Resguardo inicial

linux-7.2.3/drivers/net/ethernet/meta/fbnic/Makefile

@@ -0,0 +1,28 @@
+# SPDX-License-Identifier: GPL-2.0
+# Copyright (c) Meta Platforms, Inc. and affiliates.
+
+#
+# Makefile for the Meta(R) Host Network Interface
+#
+
+obj-$(CONFIG_FBNIC) += fbnic.o
+
+fbnic-y := fbnic_csr.o \
+	   fbnic_debugfs.o \
+	   fbnic_devlink.o \
+	   fbnic_ethtool.o \
+	   fbnic_fw.o \
+	   fbnic_fw_log.o \
+	   fbnic_hw_stats.o \
+	   fbnic_hwmon.o \
+	   fbnic_irq.o \
+	   fbnic_mac.o \
+	   fbnic_netdev.o \
+	   fbnic_pci.o \
+	   fbnic_phylink.o \
+	   fbnic_rpc.o \
+	   fbnic_mdio.o \
+	   fbnic_time.o \
+	   fbnic_tlv.o \
+	   fbnic_txrx.o \
+# End of objects

linux-7.2.3/drivers/net/ethernet/meta/fbnic/fbnic.h

@@ -0,0 +1,263 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) Meta Platforms, Inc. and affiliates. */
+
+#ifndef _FBNIC_H_
+#define _FBNIC_H_
+
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/ptp_clock_kernel.h>
+#include <linux/types.h>
+#include <linux/workqueue.h>
+
+#include "fbnic_csr.h"
+#include "fbnic_fw.h"
+#include "fbnic_fw_log.h"
+#include "fbnic_hw_stats.h"
+#include "fbnic_mac.h"
+#include "fbnic_rpc.h"
+
+struct fbnic_napi_vector;
+
+#define FBNIC_MAX_NAPI_VECTORS		128u
+#define FBNIC_MBX_CMPL_SLOTS		4
+
+struct fbnic_dev {
+	struct device *dev;
+	struct net_device *netdev;
+	struct dentry *dbg_fbd;
+	struct device *hwmon;
+	struct devlink_health_reporter *fw_reporter;
+	struct devlink_health_reporter *otp_reporter;
+
+	u32 __iomem *uc_addr0;
+	u32 __iomem *uc_addr4;
+	const struct fbnic_mac *mac;
+	unsigned int fw_msix_vector;
+	unsigned int mac_msix_vector;
+	unsigned short num_irqs;
+
+	struct {
+		u8 users;
+		char name[IFNAMSIZ + 9];
+	} napi_irq[FBNIC_MAX_NAPI_VECTORS];
+
+	struct delayed_work service_task;
+
+	struct fbnic_fw_mbx mbx[FBNIC_IPC_MBX_INDICES];
+	struct fbnic_fw_cap fw_cap;
+	struct fbnic_fw_completion *cmpl_data[FBNIC_MBX_CMPL_SLOTS];
+	/* Lock protecting Tx Mailbox queue to prevent possible races */
+	spinlock_t fw_tx_lock;
+
+	unsigned long last_heartbeat_request;
+	unsigned long last_heartbeat_response;
+	u8 fw_heartbeat_enabled;
+
+	u64 dsn;
+	u32 mps;
+	u32 readrq;
+	u8 relaxed_ord;
+
+	/* Local copy of the devices TCAM */
+	struct fbnic_act_tcam act_tcam[FBNIC_RPC_TCAM_ACT_NUM_ENTRIES];
+	struct fbnic_mac_addr mac_addr[FBNIC_RPC_TCAM_MACDA_NUM_ENTRIES];
+	u8 mac_addr_boundary;
+	u8 tce_tcam_last;
+
+	/* IP TCAM */
+	struct fbnic_ip_addr ip_src[FBNIC_RPC_TCAM_IP_ADDR_NUM_ENTRIES];
+	struct fbnic_ip_addr ip_dst[FBNIC_RPC_TCAM_IP_ADDR_NUM_ENTRIES];
+	struct fbnic_ip_addr ipo_src[FBNIC_RPC_TCAM_IP_ADDR_NUM_ENTRIES];
+	struct fbnic_ip_addr ipo_dst[FBNIC_RPC_TCAM_IP_ADDR_NUM_ENTRIES];
+
+	/* Number of TCQs/RCQs available on hardware */
+	u16 max_num_queues;
+
+	/* Lock protecting writes to @time_high, @time_offset of fbnic_netdev,
+	 * and the HW time CSR machinery.
+	 */
+	spinlock_t time_lock;
+	/* Externally accessible PTP clock, may be NULL */
+	struct ptp_clock *ptp;
+	struct ptp_clock_info ptp_info;
+	/* Last @time_high refresh time in jiffies (to catch stalls) */
+	unsigned long last_read;
+
+	/* PMD specific data */
+	unsigned long end_of_pmd_training;
+	u8 pmd_state;
+
+	/* Local copy of hardware statistics */
+	struct fbnic_hw_stats hw_stats;
+
+	/* Firmware time since boot in milliseconds */
+	u64 firmware_time;
+	u64 prev_firmware_time;
+
+	struct fbnic_fw_log fw_log;
+
+	/* MDIO bus for PHYs */
+	struct mii_bus *mdio_bus;
+
+	/* In units of ms since API supports values in ms */
+	u16 ps_timeout;
+};
+
+/* Reserve entry 0 in the MSI-X "others" array until we have filled all
+ * 32 of the possible interrupt slots. By doing this we can avoid any
+ * potential conflicts should we need to enable one of the debug interrupt
+ * causes later.
+ */
+enum {
+	FBNIC_FW_MSIX_ENTRY,
+	FBNIC_PCS_MSIX_ENTRY,
+	FBNIC_NON_NAPI_VECTORS
+};
+
+static inline bool fbnic_present(struct fbnic_dev *fbd)
+{
+	return !!READ_ONCE(fbd->uc_addr0);
+}
+
+static inline void fbnic_wr32(struct fbnic_dev *fbd, u32 reg, u32 val)
+{
+	u32 __iomem *csr = READ_ONCE(fbd->uc_addr0);
+
+	if (csr)
+		writel(val, csr + reg);
+}
+
+u32 fbnic_rd32(struct fbnic_dev *fbd, u32 reg);
+
+static inline void fbnic_wrfl(struct fbnic_dev *fbd)
+{
+	fbnic_rd32(fbd, FBNIC_MASTER_SPARE_0);
+}
+
+static inline void
+fbnic_rmw32(struct fbnic_dev *fbd, u32 reg, u32 mask, u32 val)
+{
+	u32 v;
+
+	v = fbnic_rd32(fbd, reg);
+	v &= ~mask;
+	v |= val;
+	fbnic_wr32(fbd, reg, v);
+}
+
+#define wr32(_f, _r, _v)	fbnic_wr32(_f, _r, _v)
+#define rd32(_f, _r)		fbnic_rd32(_f, _r)
+#define wrfl(_f)		fbnic_wrfl(_f)
+
+bool fbnic_fw_present(struct fbnic_dev *fbd);
+u32 fbnic_fw_rd32(struct fbnic_dev *fbd, u32 reg);
+void fbnic_fw_wr32(struct fbnic_dev *fbd, u32 reg, u32 val);
+
+#define fw_rd32(_f, _r)		fbnic_fw_rd32(_f, _r)
+#define fw_wr32(_f, _r, _v)	fbnic_fw_wr32(_f, _r, _v)
+#define fw_wrfl(_f)		fbnic_fw_rd32(_f, FBNIC_FW_ZERO_REG)
+
+static inline bool fbnic_bmc_present(struct fbnic_dev *fbd)
+{
+	return fbd->fw_cap.bmc_present;
+}
+
+static inline bool fbnic_init_failure(struct fbnic_dev *fbd)
+{
+	return !fbd->netdev;
+}
+
+extern char fbnic_driver_name[];
+
+void fbnic_devlink_free(struct fbnic_dev *fbd);
+struct fbnic_dev *fbnic_devlink_alloc(struct pci_dev *pdev);
+int fbnic_devlink_health_create(struct fbnic_dev *fbd);
+void fbnic_devlink_health_destroy(struct fbnic_dev *fbd);
+void fbnic_devlink_register(struct fbnic_dev *fbd);
+void fbnic_devlink_unregister(struct fbnic_dev *fbd);
+void __printf(2, 3)
+fbnic_devlink_fw_report(struct fbnic_dev *fbd, const char *format, ...);
+void fbnic_devlink_otp_check(struct fbnic_dev *fbd, const char *msg);
+
+int fbnic_fw_request_mbx(struct fbnic_dev *fbd);
+void fbnic_fw_free_mbx(struct fbnic_dev *fbd);
+
+void fbnic_hwmon_register(struct fbnic_dev *fbd);
+void fbnic_hwmon_unregister(struct fbnic_dev *fbd);
+
+int fbnic_mac_request_irq(struct fbnic_dev *fbd);
+void fbnic_mac_free_irq(struct fbnic_dev *fbd);
+
+void fbnic_napi_name_irqs(struct fbnic_dev *fbd);
+int fbnic_napi_request_irq(struct fbnic_dev *fbd,
+			   struct fbnic_napi_vector *nv);
+void fbnic_napi_free_irq(struct fbnic_dev *fbd,
+			 struct fbnic_napi_vector *nv);
+void fbnic_synchronize_irq(struct fbnic_dev *fbd, int nr);
+int fbnic_request_irq(struct fbnic_dev *dev, int nr, irq_handler_t handler,
+		      unsigned long flags, const char *name, void *data);
+void fbnic_free_irq(struct fbnic_dev *dev, int nr, void *data);
+
+/**
+ * enum fbnic_msix_self_test_codes - return codes from self test routines
+ *
+ * These are the codes returned from the self test routines and
+ * stored in the test result array indexed by the specific
+ * test name.
+ *
+ * @FBNIC_TEST_MSIX_SUCCESS: no errors
+ * @FBNIC_TEST_MSIX_NOMEM: allocation failure
+ * @FBNIC_TEST_MSIX_IRQ_REQ_FAIL: IRQ request failure
+ * @FBNIC_TEST_MSIX_MASK: masking failed to prevent IRQ
+ * @FBNIC_TEST_MSIX_UNMASK: unmasking failure w/ sw status set
+ * @FBNIC_TEST_MSIX_IRQ_CLEAR: interrupt when clearing mask
+ * @FBNIC_TEST_MSIX_NO_INTERRUPT: no interrupt when not masked
+ * @FBNIC_TEST_MSIX_NO_CLEAR_OR_MASK: status not cleared, or mask not set
+ * @FBNIC_TEST_MSIX_BITS_SET_AFTER_TEST: Bits are set after test
+ */
+enum fbnic_msix_self_test_codes {
+	FBNIC_TEST_MSIX_SUCCESS = 0,
+	FBNIC_TEST_MSIX_NOMEM = 5,
+	FBNIC_TEST_MSIX_IRQ_REQ_FAIL = 10,
+	FBNIC_TEST_MSIX_MASK = 20,
+	FBNIC_TEST_MSIX_UNMASK = 30,
+	FBNIC_TEST_MSIX_IRQ_CLEAR = 40,
+	FBNIC_TEST_MSIX_NO_INTERRUPT = 50,
+	FBNIC_TEST_MSIX_NO_CLEAR_OR_MASK = 60,
+	FBNIC_TEST_MSIX_BITS_SET_AFTER_TEST = 70,
+};
+
+enum fbnic_msix_self_test_codes fbnic_msix_test(struct fbnic_dev *fbd);
+
+void fbnic_free_irqs(struct fbnic_dev *fbd);
+int fbnic_alloc_irqs(struct fbnic_dev *fbd);
+
+void fbnic_get_fw_ver_commit_str(struct fbnic_dev *fbd, char *fw_version,
+				 const size_t str_sz);
+
+void fbnic_dbg_fbd_init(struct fbnic_dev *fbd);
+void fbnic_dbg_fbd_exit(struct fbnic_dev *fbd);
+void fbnic_dbg_init(void);
+void fbnic_dbg_exit(void);
+
+void fbnic_rpc_reset_valid_entries(struct fbnic_dev *fbd);
+
+int fbnic_mdiobus_create(struct fbnic_dev *fbd);
+
+void fbnic_csr_get_regs(struct fbnic_dev *fbd, u32 *data, u32 *regs_version);
+int fbnic_csr_regs_len(struct fbnic_dev *fbd);
+
+void fbnic_config_txrx_usecs(struct fbnic_napi_vector *nv, u32 arm);
+void fbnic_config_rx_frames(struct fbnic_napi_vector *nv);
+
+enum fbnic_boards {
+	fbnic_board_asic
+};
+
+struct fbnic_info {
+	unsigned int max_num_queues;
+	unsigned int bar_mask;
+};
+
+#endif /* _FBNIC_H_ */

linux-7.2.3/drivers/net/ethernet/meta/fbnic/fbnic_csr.c

@@ -0,0 +1,277 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) Meta Platforms, Inc. and affiliates. */
+
+#include "fbnic.h"
+
+#define FBNIC_BOUNDS(section) { \
+	.start = FBNIC_CSR_START_##section, \
+	.end = FBNIC_CSR_END_##section + 1, \
+}
+
+struct fbnic_csr_bounds {
+	u32	start;
+	u32	end;
+};
+
+static const struct fbnic_csr_bounds fbnic_csr_sects[] = {
+	FBNIC_BOUNDS(INTR),
+	FBNIC_BOUNDS(INTR_CQ),
+	FBNIC_BOUNDS(QM_TX),
+	FBNIC_BOUNDS(QM_RX),
+	FBNIC_BOUNDS(TCE),
+	FBNIC_BOUNDS(TCE_RAM),
+	FBNIC_BOUNDS(TMI),
+	FBNIC_BOUNDS(PTP),
+	FBNIC_BOUNDS(RXB),
+	FBNIC_BOUNDS(RPC),
+	FBNIC_BOUNDS(FAB),
+	FBNIC_BOUNDS(MASTER),
+	FBNIC_BOUNDS(PCS),
+	FBNIC_BOUNDS(RSFEC),
+	FBNIC_BOUNDS(MAC_MAC),
+	FBNIC_BOUNDS(SIG),
+	FBNIC_BOUNDS(PCIE_SS_COMPHY),
+	FBNIC_BOUNDS(PUL_USER),
+	FBNIC_BOUNDS(QUEUE),
+	FBNIC_BOUNDS(RPC_RAM),
+};
+
+#define FBNIC_RPC_TCAM_ACT_DW_PER_ENTRY			14
+#define FBNIC_RPC_TCAM_ACT_NUM_ENTRIES			64
+
+#define FBNIC_RPC_TCAM_MACDA_DW_PER_ENTRY		4
+#define FBNIC_RPC_TCAM_MACDA_NUM_ENTRIES		32
+
+#define FBNIC_RPC_TCAM_OUTER_IPSRC_DW_PER_ENTRY		9
+#define FBNIC_RPC_TCAM_OUTER_IPSRC_NUM_ENTRIES		8
+
+#define FBNIC_RPC_TCAM_OUTER_IPDST_DW_PER_ENTRY		9
+#define FBNIC_RPC_TCAM_OUTER_IPDST_NUM_ENTRIES		8
+
+#define FBNIC_RPC_TCAM_IPSRC_DW_PER_ENTRY		9
+#define FBNIC_RPC_TCAM_IPSRC_NUM_ENTRIES		8
+
+#define FBNIC_RPC_TCAM_IPDST_DW_PER_ENTRY		9
+#define FBNIC_RPC_TCAM_IPDST_NUM_ENTRIES		8
+
+#define FBNIC_RPC_RSS_TBL_DW_PER_ENTRY			2
+#define FBNIC_RPC_RSS_TBL_NUM_ENTRIES			256
+
+static void fbnic_csr_get_regs_rpc_ram(struct fbnic_dev *fbd, u32 **data_p)
+{
+	u32 start = FBNIC_CSR_START_RPC_RAM;
+	u32 end = FBNIC_CSR_END_RPC_RAM;
+	u32 *data = *data_p;
+	u32 i, j;
+
+	*(data++) = start;
+	*(data++) = end;
+
+	/* FBNIC_RPC_TCAM_ACT */
+	for (i = 0; i < FBNIC_RPC_TCAM_ACT_NUM_ENTRIES; i++) {
+		for (j = 0; j < FBNIC_RPC_TCAM_ACT_DW_PER_ENTRY; j++)
+			*(data++) = rd32(fbd, FBNIC_RPC_TCAM_ACT(i, j));
+	}
+
+	/* FBNIC_RPC_TCAM_MACDA */
+	for (i = 0; i < FBNIC_RPC_TCAM_MACDA_NUM_ENTRIES; i++) {
+		for (j = 0; j < FBNIC_RPC_TCAM_MACDA_DW_PER_ENTRY; j++)
+			*(data++) = rd32(fbd, FBNIC_RPC_TCAM_MACDA(i, j));
+	}
+
+	/* FBNIC_RPC_TCAM_OUTER_IPSRC */
+	for (i = 0; i < FBNIC_RPC_TCAM_OUTER_IPSRC_NUM_ENTRIES; i++) {
+		for (j = 0; j < FBNIC_RPC_TCAM_OUTER_IPSRC_DW_PER_ENTRY; j++)
+			*(data++) = rd32(fbd, FBNIC_RPC_TCAM_OUTER_IPSRC(i, j));
+	}
+
+	/* FBNIC_RPC_TCAM_OUTER_IPDST */
+	for (i = 0; i < FBNIC_RPC_TCAM_OUTER_IPDST_NUM_ENTRIES; i++) {
+		for (j = 0; j < FBNIC_RPC_TCAM_OUTER_IPDST_DW_PER_ENTRY; j++)
+			*(data++) = rd32(fbd, FBNIC_RPC_TCAM_OUTER_IPDST(i, j));
+	}
+
+	/* FBNIC_RPC_TCAM_IPSRC */
+	for (i = 0; i < FBNIC_RPC_TCAM_IPSRC_NUM_ENTRIES; i++) {
+		for (j = 0; j < FBNIC_RPC_TCAM_IPSRC_DW_PER_ENTRY; j++)
+			*(data++) = rd32(fbd, FBNIC_RPC_TCAM_IPSRC(i, j));
+	}
+
+	/* FBNIC_RPC_TCAM_IPDST */
+	for (i = 0; i < FBNIC_RPC_TCAM_IPDST_NUM_ENTRIES; i++) {
+		for (j = 0; j < FBNIC_RPC_TCAM_IPDST_DW_PER_ENTRY; j++)
+			*(data++) = rd32(fbd, FBNIC_RPC_TCAM_IPDST(i, j));
+	}
+
+	/* FBNIC_RPC_RSS_TBL */
+	for (i = 0; i < FBNIC_RPC_RSS_TBL_NUM_ENTRIES; i++) {
+		for (j = 0; j < FBNIC_RPC_RSS_TBL_DW_PER_ENTRY; j++)
+			*(data++) = rd32(fbd, FBNIC_RPC_RSS_TBL(i, j));
+	}
+
+	*data_p = data;
+}
+
+void fbnic_csr_get_regs(struct fbnic_dev *fbd, u32 *data, u32 *regs_version)
+{
+	const struct fbnic_csr_bounds *bound;
+	u32 *start = data;
+	int i, j;
+
+	*regs_version = 1u;
+
+	/* Skip RPC_RAM section which cannot be dumped linearly */
+	for (i = 0, bound = fbnic_csr_sects;
+	     i < ARRAY_SIZE(fbnic_csr_sects) - 1; i++, ++bound) {
+		*(data++) = bound->start;
+		*(data++) = bound->end - 1;
+		for (j = bound->start; j < bound->end; j++)
+			*(data++) = rd32(fbd, j);
+	}
+
+	/* Dump the RPC_RAM as special case registers */
+	fbnic_csr_get_regs_rpc_ram(fbd, &data);
+
+	WARN_ON(data - start != fbnic_csr_regs_len(fbd));
+}
+
+int fbnic_csr_regs_len(struct fbnic_dev *fbd)
+{
+	int i, len = 0;
+
+	/* Dump includes start and end information of each section
+	 * which results in an offset of 2
+	 */
+	for (i = 0; i < ARRAY_SIZE(fbnic_csr_sects); i++)
+		len += fbnic_csr_sects[i].end - fbnic_csr_sects[i].start + 2;
+
+	return len;
+}
+
+/* CSR register test data
+ *
+ * The register test will be used to verify hardware is behaving as expected.
+ *
+ * The test itself will have us writing to registers that should have no
+ * side effects due to us resetting after the test has been completed.
+ * While the test is being run the interface should be offline.
+ */
+struct fbnic_csr_reg_test_data {
+	int	reg;
+	u16	reg_offset;
+	u8	array_len;
+	u32	read;
+	u32	write;
+};
+
+#define FBNIC_QUEUE_REG_TEST(_name, _read, _write) { \
+	.reg = FBNIC_QUEUE(0) + FBNIC_QUEUE_##_name, \
+	.reg_offset = FBNIC_QUEUE_STRIDE, \
+	.array_len = 64, \
+	.read = _read, \
+	.write = _write \
+}
+
+static const struct fbnic_csr_reg_test_data pattern_test[] = {
+	FBNIC_QUEUE_REG_TEST(TWQ0_CTL, FBNIC_QUEUE_TWQ_CTL_RESET,
+			     FBNIC_QUEUE_TWQ_CTL_RESET),
+	FBNIC_QUEUE_REG_TEST(TWQ0_PTRS, 0, ~0),
+	FBNIC_QUEUE_REG_TEST(TWQ0_SIZE, FBNIC_QUEUE_TWQ_SIZE_MASK, ~0),
+	FBNIC_QUEUE_REG_TEST(TWQ0_BAL, FBNIC_QUEUE_BAL_MASK, ~0),
+	FBNIC_QUEUE_REG_TEST(TWQ0_BAH, ~0, ~0),
+	FBNIC_QUEUE_REG_TEST(TWQ1_CTL, FBNIC_QUEUE_TWQ_CTL_RESET,
+			     FBNIC_QUEUE_TWQ_CTL_RESET),
+	FBNIC_QUEUE_REG_TEST(TWQ1_PTRS, 0, ~0),
+	FBNIC_QUEUE_REG_TEST(TWQ1_SIZE, FBNIC_QUEUE_TWQ_SIZE_MASK, ~0),
+	FBNIC_QUEUE_REG_TEST(TWQ1_BAL, FBNIC_QUEUE_BAL_MASK, ~0),
+	FBNIC_QUEUE_REG_TEST(TWQ1_BAH, ~0, ~0),
+	FBNIC_QUEUE_REG_TEST(TCQ_CTL, FBNIC_QUEUE_TCQ_CTL_RESET,
+			     FBNIC_QUEUE_TCQ_CTL_RESET),
+	FBNIC_QUEUE_REG_TEST(TCQ_PTRS, 0, ~0),
+	FBNIC_QUEUE_REG_TEST(TCQ_SIZE, FBNIC_QUEUE_TCQ_SIZE_MASK, ~0),
+	FBNIC_QUEUE_REG_TEST(TCQ_BAL, FBNIC_QUEUE_BAL_MASK, ~0),
+	FBNIC_QUEUE_REG_TEST(TCQ_BAH, ~0, ~0),
+	FBNIC_QUEUE_REG_TEST(RCQ_CTL, FBNIC_QUEUE_RCQ_CTL_RESET,
+			     FBNIC_QUEUE_RCQ_CTL_RESET),
+	FBNIC_QUEUE_REG_TEST(RCQ_PTRS, 0, ~0),
+	FBNIC_QUEUE_REG_TEST(RCQ_SIZE, FBNIC_QUEUE_RCQ_SIZE_MASK, ~0),
+	FBNIC_QUEUE_REG_TEST(RCQ_BAL, FBNIC_QUEUE_BAL_MASK, ~0),
+	FBNIC_QUEUE_REG_TEST(RCQ_BAH, ~0, ~0),
+	FBNIC_QUEUE_REG_TEST(BDQ_CTL, FBNIC_QUEUE_BDQ_CTL_RESET,
+			     FBNIC_QUEUE_BDQ_CTL_RESET),
+	FBNIC_QUEUE_REG_TEST(BDQ_HPQ_PTRS, 0, ~0),
+	FBNIC_QUEUE_REG_TEST(BDQ_HPQ_SIZE, FBNIC_QUEUE_BDQ_SIZE_MASK, ~0),
+	FBNIC_QUEUE_REG_TEST(BDQ_HPQ_BAL, FBNIC_QUEUE_BAL_MASK, ~0),
+	FBNIC_QUEUE_REG_TEST(BDQ_HPQ_BAH, ~0, ~0),
+	FBNIC_QUEUE_REG_TEST(BDQ_PPQ_PTRS, 0, ~0),
+	FBNIC_QUEUE_REG_TEST(BDQ_PPQ_SIZE, FBNIC_QUEUE_BDQ_SIZE_MASK, ~0),
+	FBNIC_QUEUE_REG_TEST(BDQ_PPQ_BAL, FBNIC_QUEUE_BAL_MASK, ~0),
+	FBNIC_QUEUE_REG_TEST(BDQ_PPQ_BAH, ~0, ~0),
+};
+
+static enum fbnic_reg_self_test_codes
+fbnic_csr_reg_pattern_test(struct fbnic_dev *fbd, int index,
+			   const struct fbnic_csr_reg_test_data *test_data)
+{
+	static const u32 pattern[] = { ~0, 0x5A5A5A5A, 0xA5A5A5A5, 0};
+	enum fbnic_reg_self_test_codes reg;
+	int i;
+
+	reg = test_data->reg + test_data->reg_offset * index;
+	for (i = 0; i < ARRAY_SIZE(pattern); i++) {
+		u32 val = pattern[i] & test_data->write;
+		u32 result;
+
+		wr32(fbd, reg, val);
+		result = rd32(fbd, reg);
+		val &= test_data->read;
+
+		if (result == val)
+			continue;
+
+		dev_err(fbd->dev,
+			"%s: reg 0x%06X failed, expected 0x%08X received 0x%08X\n",
+			__func__, reg, val, result);
+
+		/* Note that FBNIC_INTR_STATUS(0) could be tested and fail
+		 * and the result would not be reported since the register
+		 * offset is 0. However as that register isn't included in
+		 * the register test that isn't an issue.
+		 */
+		return reg;
+	}
+
+	return FBNIC_REG_TEST_SUCCESS;
+}
+
+/**
+ * fbnic_csr_regs_test() - Verify behavior of NIC registers
+ * @fbd: device to test
+ *
+ * This function is meant to test the bit values of various registers in
+ * the NIC device. Specifically this test will verify which bits are
+ * writable and which ones are not. It will write varying patterns of bits
+ * to the registers testing for sticky bits, or bits that are writable but
+ * should not be.
+ *
+ * Return: FBNIC_REG_TEST_SUCCESS on success, register number on failure
+ **/
+enum fbnic_reg_self_test_codes fbnic_csr_regs_test(struct fbnic_dev *fbd)
+{
+	const struct fbnic_csr_reg_test_data *test_data;
+
+	for (test_data = pattern_test;
+	     test_data < pattern_test + ARRAY_SIZE(pattern_test); test_data++) {
+		u32 i;
+
+		for (i = 0; i < test_data->array_len; i++) {
+			enum fbnic_reg_self_test_codes reg =
+				fbnic_csr_reg_pattern_test(fbd, i, test_data);
+
+			if (reg)
+				return reg;
+		}
+	}
+
+	return FBNIC_REG_TEST_SUCCESS;
+}

linux-7.2.3/drivers/net/ethernet/meta/fbnic/fbnic_debugfs.c

@@ -0,0 +1,678 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) Meta Platforms, Inc. and affiliates. */
+
+#include <linux/debugfs.h>
+#include <linux/pci.h>
+#include <linux/rtnetlink.h>
+#include <linux/seq_file.h>
+
+#include "fbnic.h"
+#include "fbnic_txrx.h"
+
+static struct dentry *fbnic_dbg_root;
+
+/* Descriptor Seq Functions */
+
+static void fbnic_dbg_desc_break(struct seq_file *s, int i)
+{
+	while (i--)
+		seq_putc(s, '-');
+
+	seq_putc(s, '\n');
+}
+
+static void fbnic_dbg_ring_show(struct seq_file *s)
+{
+	struct fbnic_ring *ring = s->private;
+	unsigned long doorbell_offset;
+	u32 head = 0, tail = 0;
+	u32 __iomem *csr_base;
+
+	csr_base = fbnic_ring_csr_base(ring);
+	doorbell_offset = ring->doorbell - csr_base;
+
+	seq_printf(s, "doorbell CSR: %#05lx q_idx: %d\n",
+		   doorbell_offset, ring->q_idx);
+	seq_printf(s, "size_mask: %#06x size: %zu flags: 0x%02x\n",
+		   ring->size_mask, ring->size, ring->flags);
+	seq_printf(s, "SW: head: %#06x tail: %#06x\n",
+		   ring->head, ring->tail);
+
+	switch (doorbell_offset) {
+	case FBNIC_QUEUE_TWQ0_TAIL:
+		tail = readl(csr_base + FBNIC_QUEUE_TWQ0_PTRS);
+		head = FIELD_GET(FBNIC_QUEUE_TWQ_PTRS_HEAD_MASK, tail);
+		break;
+	case FBNIC_QUEUE_TWQ1_TAIL:
+		tail = readl(csr_base + FBNIC_QUEUE_TWQ1_PTRS);
+		head = FIELD_GET(FBNIC_QUEUE_TWQ_PTRS_HEAD_MASK, tail);
+		break;
+	case FBNIC_QUEUE_TCQ_HEAD:
+		head = readl(csr_base + FBNIC_QUEUE_TCQ_PTRS);
+		tail = FIELD_GET(FBNIC_QUEUE_TCQ_PTRS_TAIL_MASK, head);
+		break;
+	case FBNIC_QUEUE_BDQ_HPQ_TAIL:
+		tail = readl(csr_base + FBNIC_QUEUE_BDQ_HPQ_PTRS);
+		head = FIELD_GET(FBNIC_QUEUE_BDQ_PTRS_HEAD_MASK, tail);
+		break;
+	case FBNIC_QUEUE_BDQ_PPQ_TAIL:
+		tail = readl(csr_base + FBNIC_QUEUE_BDQ_PPQ_PTRS);
+		head = FIELD_GET(FBNIC_QUEUE_BDQ_PTRS_HEAD_MASK, tail);
+		break;
+	case FBNIC_QUEUE_RCQ_HEAD:
+		head = readl(csr_base + FBNIC_QUEUE_RCQ_PTRS);
+		tail = FIELD_GET(FBNIC_QUEUE_RCQ_PTRS_TAIL_MASK, head);
+		break;
+	}
+
+	tail &= FBNIC_QUEUE_BDQ_PTRS_TAIL_MASK;
+	head &= FBNIC_QUEUE_RCQ_PTRS_HEAD_MASK;
+
+	seq_printf(s, "HW: head: %#06x tail: %#06x\n", head, tail);
+
+	seq_puts(s, "\n");
+}
+
+static void fbnic_dbg_twd_desc_seq_show(struct seq_file *s, int i)
+{
+	struct fbnic_ring *ring = s->private;
+	u64 twd = le64_to_cpu(ring->desc[i]);
+
+	switch (FIELD_GET(FBNIC_TWD_TYPE_MASK, twd)) {
+	case FBNIC_TWD_TYPE_META:
+		seq_printf(s, "%04x %#06llx  %llx %llx %llx %llx %llx %#llx %#llx %llx %#04llx %#04llx %llx %#04llx\n",
+			   i, FIELD_GET(FBNIC_TWD_LEN_MASK, twd),
+			   FIELD_GET(FBNIC_TWD_TYPE_MASK, twd),
+			   FIELD_GET(FBNIC_TWD_FLAG_REQ_COMPLETION, twd),
+			   FIELD_GET(FBNIC_TWD_FLAG_REQ_CSO, twd),
+			   FIELD_GET(FBNIC_TWD_FLAG_REQ_LSO, twd),
+			   FIELD_GET(FBNIC_TWD_FLAG_REQ_TS, twd),
+			   FIELD_GET(FBNIC_TWD_L4_HLEN_MASK, twd),
+			   FIELD_GET(FBNIC_TWD_CSUM_OFFSET_MASK, twd),
+			   FIELD_GET(FBNIC_TWD_L4_TYPE_MASK, twd),
+			   FIELD_GET(FBNIC_TWD_L3_IHLEN_MASK, twd),
+			   FIELD_GET(FBNIC_TWD_L3_OHLEN_MASK, twd),
+			   FIELD_GET(FBNIC_TWD_L3_TYPE_MASK, twd),
+			   FIELD_GET(FBNIC_TWD_L2_HLEN_MASK, twd));
+		break;
+	default:
+		seq_printf(s, "%04x %#06llx  %llx %#014llx\n", i,
+			   FIELD_GET(FBNIC_TWD_LEN_MASK, twd),
+			   FIELD_GET(FBNIC_TWD_TYPE_MASK, twd),
+			   FIELD_GET(FBNIC_TWD_ADDR_MASK, twd));
+		break;
+	}
+}
+
+static int fbnic_dbg_twq_desc_seq_show(struct seq_file *s, void *v)
+{
+	struct fbnic_ring *ring = s->private;
+	char hdr[80];
+	int i;
+
+	/* Generate header on first entry */
+	fbnic_dbg_ring_show(s);
+	snprintf(hdr, sizeof(hdr), "%4s %5s %s %s\n",
+		 "DESC", "LEN/MSS", "T", "METADATA/TIMESTAMP/BUFFER_ADDR");
+	seq_puts(s, hdr);
+	fbnic_dbg_desc_break(s, strnlen(hdr, sizeof(hdr)));
+
+	/* Display descriptor */
+	if (!ring->desc) {
+		seq_puts(s, "Descriptor ring not allocated.\n");
+		return 0;
+	}
+
+	for (i = 0; i <= ring->size_mask; i++)
+		fbnic_dbg_twd_desc_seq_show(s, i);
+
+	return 0;
+}
+
+static int fbnic_dbg_tcq_desc_seq_show(struct seq_file *s, void *v)
+{
+	struct fbnic_ring *ring = s->private;
+	char hdr[80];
+	int i;
+
+	/* Generate header on first entry */
+	fbnic_dbg_ring_show(s);
+	snprintf(hdr, sizeof(hdr), "%4s %s %s %s %5s %-16s %-6s %-6s\n",
+		 "DESC", "D", "T", "Q", "STATUS", "TIMESTAMP", "HEAD1", "HEAD0");
+	seq_puts(s, hdr);
+	fbnic_dbg_desc_break(s, strnlen(hdr, sizeof(hdr)));
+
+	/* Display descriptor */
+	if (!ring->desc) {
+		seq_puts(s, "Descriptor ring not allocated.\n");
+		return 0;
+	}
+
+	for (i = 0; i <= ring->size_mask; i++) {
+		u64 tcd = le64_to_cpu(ring->desc[i]);
+
+		switch (FIELD_GET(FBNIC_TCD_TYPE_MASK, tcd)) {
+		case FBNIC_TCD_TYPE_0:
+			seq_printf(s, "%04x %llx %llx %llx %#05llx %-17s %#06llx %#06llx\n",
+				   i, FIELD_GET(FBNIC_TCD_DONE, tcd),
+				   FIELD_GET(FBNIC_TCD_TYPE_MASK, tcd),
+				   FIELD_GET(FBNIC_TCD_TWQ1, tcd),
+				   FIELD_GET(FBNIC_TCD_STATUS_MASK, tcd),
+				   "",
+				   FIELD_GET(FBNIC_TCD_TYPE0_HEAD1_MASK, tcd),
+				   FIELD_GET(FBNIC_TCD_TYPE0_HEAD0_MASK, tcd));
+			break;
+		case FBNIC_TCD_TYPE_1:
+			seq_printf(s, "%04x %llx %llx %llx %#05llx  %#012llx\n",
+				   i, FIELD_GET(FBNIC_TCD_DONE, tcd),
+				   FIELD_GET(FBNIC_TCD_TYPE_MASK, tcd),
+				   FIELD_GET(FBNIC_TCD_TWQ1, tcd),
+				   FIELD_GET(FBNIC_TCD_STATUS_MASK, tcd),
+				   FIELD_GET(FBNIC_TCD_TYPE1_TS_MASK, tcd));
+			break;
+		default:
+			break;
+		}
+	}
+
+	return 0;
+}
+
+static int fbnic_dbg_bdq_desc_seq_show(struct seq_file *s, void *v)
+{
+	struct fbnic_ring *ring = s->private;
+	char hdr[80];
+	int i;
+
+	/* Generate header on first entry */
+	fbnic_dbg_ring_show(s);
+	snprintf(hdr, sizeof(hdr), "%4s %-4s %s\n",
+		 "DESC", "ID", "BUFFER_ADDR");
+	seq_puts(s, hdr);
+	fbnic_dbg_desc_break(s, strnlen(hdr, sizeof(hdr)));
+
+	/* Display descriptor */
+	if (!ring->desc) {
+		seq_puts(s, "Descriptor ring not allocated.\n");
+		return 0;
+	}
+
+	for (i = 0; i < (ring->size_mask + 1) * FBNIC_BD_FRAG_COUNT; i++) {
+		u64 bd = le64_to_cpu(ring->desc[i]);
+
+		seq_printf(s, "%04x %#04llx %#014llx\n", i,
+			   FIELD_GET(FBNIC_BD_DESC_ID_MASK, bd),
+			   FIELD_GET(FBNIC_BD_DESC_ADDR_MASK, bd));
+	}
+
+	return 0;
+}
+
+static void fbnic_dbg_rcd_desc_seq_show(struct seq_file *s, int i)
+{
+	struct fbnic_ring *ring = s->private;
+	u64 rcd = le64_to_cpu(ring->desc[i]);
+
+	switch (FIELD_GET(FBNIC_RCD_TYPE_MASK, rcd)) {
+	case FBNIC_RCD_TYPE_HDR_AL:
+	case FBNIC_RCD_TYPE_PAY_AL:
+		seq_printf(s, "%04x %llx %llx %llx %#06llx      %#06llx   %#06llx\n",
+			   i, FIELD_GET(FBNIC_RCD_DONE, rcd),
+			   FIELD_GET(FBNIC_RCD_TYPE_MASK, rcd),
+			   FIELD_GET(FBNIC_RCD_AL_PAGE_FIN, rcd),
+			   FIELD_GET(FBNIC_RCD_AL_BUFF_OFF_MASK, rcd),
+			   FIELD_GET(FBNIC_RCD_AL_BUFF_LEN_MASK, rcd),
+			   FIELD_GET(FBNIC_RCD_AL_BUFF_ID_MASK, rcd));
+		break;
+	case FBNIC_RCD_TYPE_OPT_META:
+		seq_printf(s, "%04x %llx %llx %llx %llx %llx      %#06llx   %#012llx\n",
+			   i, FIELD_GET(FBNIC_RCD_DONE, rcd),
+			   FIELD_GET(FBNIC_RCD_TYPE_MASK, rcd),
+			   FIELD_GET(FBNIC_RCD_OPT_META_TYPE_MASK, rcd),
+			   FIELD_GET(FBNIC_RCD_OPT_META_TS, rcd),
+			   FIELD_GET(FBNIC_RCD_OPT_META_ACTION, rcd),
+			   FIELD_GET(FBNIC_RCD_OPT_META_ACTION_MASK, rcd),
+			   FIELD_GET(FBNIC_RCD_OPT_META_TS_MASK, rcd));
+		break;
+	case FBNIC_RCD_TYPE_META:
+		seq_printf(s, "%04x %llx %llx %llx %llx %llx %llx %llx %llx %llx %#06llx   %#010llx\n",
+			   i, FIELD_GET(FBNIC_RCD_DONE, rcd),
+			   FIELD_GET(FBNIC_RCD_TYPE_MASK, rcd),
+			   FIELD_GET(FBNIC_RCD_META_ECN, rcd),
+			   FIELD_GET(FBNIC_RCD_META_L4_CSUM_UNNECESSARY, rcd),
+			   FIELD_GET(FBNIC_RCD_META_ERR_MAC_EOP, rcd),
+			   FIELD_GET(FBNIC_RCD_META_ERR_TRUNCATED_FRAME, rcd),
+			   FIELD_GET(FBNIC_RCD_META_ERR_PARSER, rcd),
+			   FIELD_GET(FBNIC_RCD_META_L4_TYPE_MASK, rcd),
+			   FIELD_GET(FBNIC_RCD_META_L3_TYPE_MASK, rcd),
+			   FIELD_GET(FBNIC_RCD_META_L2_CSUM_MASK, rcd),
+			   FIELD_GET(FBNIC_RCD_META_RSS_HASH_MASK, rcd));
+		break;
+	}
+}
+
+static int fbnic_dbg_rcq_desc_seq_show(struct seq_file *s, void *v)
+{
+	struct fbnic_ring *ring = s->private;
+	char hdr[80];
+	int i;
+
+	/* Generate header on first entry */
+	fbnic_dbg_ring_show(s);
+	snprintf(hdr, sizeof(hdr),
+		 "%18s %s %s\n", "OFFSET/", "L", "L");
+	seq_puts(s, hdr);
+	snprintf(hdr, sizeof(hdr),
+		 "%4s %s %s %s %s %s %s %s %s %s %-8s %s\n",
+		 "DESC", "D", "T", "F", "C", "M", "T", "P", "4", "3", "LEN/CSUM", "ID/TS/RSS");
+	seq_puts(s, hdr);
+	fbnic_dbg_desc_break(s, strnlen(hdr, sizeof(hdr)));
+
+	/* Display descriptor */
+	if (!ring->desc) {
+		seq_puts(s, "Descriptor ring not allocated.\n");
+		return 0;
+	}
+
+	for (i = 0; i <= ring->size_mask; i++)
+		fbnic_dbg_rcd_desc_seq_show(s, i);
+
+	return 0;
+}
+
+static int fbnic_dbg_desc_open(struct inode *inode, struct file *file)
+{
+	struct fbnic_ring *ring = inode->i_private;
+	int (*show)(struct seq_file *s, void *v);
+
+	switch (ring->doorbell - fbnic_ring_csr_base(ring)) {
+	case FBNIC_QUEUE_TWQ0_TAIL:
+	case FBNIC_QUEUE_TWQ1_TAIL:
+		show = fbnic_dbg_twq_desc_seq_show;
+		break;
+	case FBNIC_QUEUE_TCQ_HEAD:
+		show = fbnic_dbg_tcq_desc_seq_show;
+		break;
+	case FBNIC_QUEUE_BDQ_HPQ_TAIL:
+	case FBNIC_QUEUE_BDQ_PPQ_TAIL:
+		show = fbnic_dbg_bdq_desc_seq_show;
+		break;
+	case FBNIC_QUEUE_RCQ_HEAD:
+		show = fbnic_dbg_rcq_desc_seq_show;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return single_open(file, show, ring);
+}
+
+static const struct file_operations fbnic_dbg_desc_fops = {
+	.owner		= THIS_MODULE,
+	.open		= fbnic_dbg_desc_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
+
+void fbnic_dbg_nv_init(struct fbnic_napi_vector *nv)
+{
+	struct fbnic_dev *fbd = nv->fbd;
+	char name[16];
+	int i, j;
+
+	/* Generate a folder for each napi vector */
+	snprintf(name, sizeof(name), "nv.%03d", nv->v_idx);
+
+	nv->dbg_nv = debugfs_create_dir(name, fbd->dbg_fbd);
+
+	/* Generate a file for each Tx ring in the napi vector */
+	for (i = 0; i < nv->txt_count; i++) {
+		struct fbnic_q_triad *qt = &nv->qt[i];
+		unsigned int hw_idx;
+
+		hw_idx = fbnic_ring_csr_base(&qt->cmpl) -
+			  &fbd->uc_addr0[FBNIC_QUEUE(0)];
+		hw_idx /= FBNIC_QUEUE_STRIDE;
+
+		snprintf(name, sizeof(name), "twq0.%03d", hw_idx);
+		debugfs_create_file(name, 0400, nv->dbg_nv, &qt->sub0,
+				    &fbnic_dbg_desc_fops);
+
+		snprintf(name, sizeof(name), "twq1.%03d", hw_idx);
+		debugfs_create_file(name, 0400, nv->dbg_nv, &qt->sub1,
+				    &fbnic_dbg_desc_fops);
+
+		snprintf(name, sizeof(name), "tcq.%03d", hw_idx);
+		debugfs_create_file(name, 0400, nv->dbg_nv, &qt->cmpl,
+				    &fbnic_dbg_desc_fops);
+	}
+
+	/* Generate a file for each Rx ring in the napi vector */
+	for (j = 0; j < nv->rxt_count; j++, i++) {
+		struct fbnic_q_triad *qt = &nv->qt[i];
+		unsigned int hw_idx;
+
+		hw_idx = fbnic_ring_csr_base(&qt->cmpl) -
+			  &fbd->uc_addr0[FBNIC_QUEUE(0)];
+		hw_idx /= FBNIC_QUEUE_STRIDE;
+
+		snprintf(name, sizeof(name), "hpq.%03d", hw_idx);
+		debugfs_create_file(name, 0400, nv->dbg_nv, &qt->sub0,
+				    &fbnic_dbg_desc_fops);
+
+		snprintf(name, sizeof(name), "ppq.%03d", hw_idx);
+		debugfs_create_file(name, 0400, nv->dbg_nv, &qt->sub1,
+				    &fbnic_dbg_desc_fops);
+
+		snprintf(name, sizeof(name), "rcq.%03d", hw_idx);
+		debugfs_create_file(name, 0400, nv->dbg_nv, &qt->cmpl,
+				    &fbnic_dbg_desc_fops);
+	}
+}
+
+void fbnic_dbg_nv_exit(struct fbnic_napi_vector *nv)
+{
+	debugfs_remove_recursive(nv->dbg_nv);
+	nv->dbg_nv = NULL;
+}
+
+static int fbnic_dbg_mac_addr_show(struct seq_file *s, void *v)
+{
+	struct fbnic_dev *fbd = s->private;
+	char hdr[80];
+	int i;
+
+	/* Generate Header */
+	snprintf(hdr, sizeof(hdr), "%3s %s %-17s %s\n",
+		 "Idx", "S", "TCAM Bitmap", "Addr/Mask");
+	seq_puts(s, hdr);
+	fbnic_dbg_desc_break(s, strnlen(hdr, sizeof(hdr)));
+
+	for (i = 0; i < FBNIC_RPC_TCAM_MACDA_NUM_ENTRIES; i++) {
+		struct fbnic_mac_addr *mac_addr = &fbd->mac_addr[i];
+
+		seq_printf(s, "%02d  %d %64pb %pm\n",
+			   i, mac_addr->state, mac_addr->act_tcam,
+			   mac_addr->value.addr8);
+		seq_printf(s, "                        %pm\n",
+			   mac_addr->mask.addr8);
+	}
+
+	return 0;
+}
+DEFINE_SHOW_ATTRIBUTE(fbnic_dbg_mac_addr);
+
+static int fbnic_dbg_tce_tcam_show(struct seq_file *s, void *v)
+{
+	struct fbnic_dev *fbd = s->private;
+	int i, tcam_idx = 0;
+	char hdr[80];
+
+	/* Generate Header */
+	snprintf(hdr, sizeof(hdr), "%3s %s %-17s %s\n",
+		 "Idx", "S", "TCAM Bitmap", "Addr/Mask");
+	seq_puts(s, hdr);
+	fbnic_dbg_desc_break(s, strnlen(hdr, sizeof(hdr)));
+
+	for (i = 0; i < ARRAY_SIZE(fbd->mac_addr); i++) {
+		struct fbnic_mac_addr *mac_addr = &fbd->mac_addr[i];
+
+		/* Verify BMC bit is set */
+		if (!test_bit(FBNIC_MAC_ADDR_T_BMC, mac_addr->act_tcam))
+			continue;
+
+		if (tcam_idx == FBNIC_TCE_TCAM_NUM_ENTRIES)
+			break;
+
+		seq_printf(s, "%02d  %d %64pb %pm\n",
+			   tcam_idx, mac_addr->state, mac_addr->act_tcam,
+			   mac_addr->value.addr8);
+		seq_printf(s, "                        %pm\n",
+			   mac_addr->mask.addr8);
+		tcam_idx++;
+	}
+
+	return 0;
+}
+DEFINE_SHOW_ATTRIBUTE(fbnic_dbg_tce_tcam);
+
+static int fbnic_dbg_act_tcam_show(struct seq_file *s, void *v)
+{
+	struct fbnic_dev *fbd = s->private;
+	char hdr[80];
+	int i;
+
+	/* Generate Header */
+	snprintf(hdr, sizeof(hdr), "%3s %s %-55s %-4s %s\n",
+		 "Idx", "S", "Value/Mask", "RSS", "Dest");
+	seq_puts(s, hdr);
+	fbnic_dbg_desc_break(s, strnlen(hdr, sizeof(hdr)));
+
+	for (i = 0; i < FBNIC_RPC_TCAM_ACT_NUM_ENTRIES; i++) {
+		struct fbnic_act_tcam *act_tcam = &fbd->act_tcam[i];
+
+		seq_printf(s, "%02d  %d %04x %04x %04x %04x %04x %04x %04x %04x %04x %04x %04x  %04x %08x\n",
+			   i, act_tcam->state,
+			   act_tcam->value.tcam[10], act_tcam->value.tcam[9],
+			   act_tcam->value.tcam[8], act_tcam->value.tcam[7],
+			   act_tcam->value.tcam[6], act_tcam->value.tcam[5],
+			   act_tcam->value.tcam[4], act_tcam->value.tcam[3],
+			   act_tcam->value.tcam[2], act_tcam->value.tcam[1],
+			   act_tcam->value.tcam[0], act_tcam->rss_en_mask,
+			   act_tcam->dest);
+		seq_printf(s, "      %04x %04x %04x %04x %04x %04x %04x %04x %04x %04x %04x\n",
+			   act_tcam->mask.tcam[10], act_tcam->mask.tcam[9],
+			   act_tcam->mask.tcam[8], act_tcam->mask.tcam[7],
+			   act_tcam->mask.tcam[6], act_tcam->mask.tcam[5],
+			   act_tcam->mask.tcam[4], act_tcam->mask.tcam[3],
+			   act_tcam->mask.tcam[2], act_tcam->mask.tcam[1],
+			   act_tcam->mask.tcam[0]);
+	}
+
+	return 0;
+}
+DEFINE_SHOW_ATTRIBUTE(fbnic_dbg_act_tcam);
+
+static int fbnic_dbg_ip_addr_show(struct seq_file *s,
+				  struct fbnic_ip_addr *ip_addr)
+{
+	char hdr[80];
+	int i;
+
+	/* Generate Header */
+	snprintf(hdr, sizeof(hdr), "%3s %s %-17s %s %s\n",
+		 "Idx", "S", "TCAM Bitmap", "V", "Addr/Mask");
+	seq_puts(s, hdr);
+	fbnic_dbg_desc_break(s, strnlen(hdr, sizeof(hdr)));
+
+	for (i = 0; i < FBNIC_RPC_TCAM_IP_ADDR_NUM_ENTRIES; i++, ip_addr++) {
+		seq_printf(s, "%02d  %d %64pb %d %pi6\n",
+			   i, ip_addr->state, ip_addr->act_tcam,
+			   ip_addr->version, &ip_addr->value);
+		seq_printf(s, "                          %pi6\n",
+			   &ip_addr->mask);
+	}
+
+	return 0;
+}
+
+static int fbnic_dbg_ip_src_show(struct seq_file *s, void *v)
+{
+	struct fbnic_dev *fbd = s->private;
+
+	return fbnic_dbg_ip_addr_show(s, fbd->ip_src);
+}
+DEFINE_SHOW_ATTRIBUTE(fbnic_dbg_ip_src);
+
+static int fbnic_dbg_ip_dst_show(struct seq_file *s, void *v)
+{
+	struct fbnic_dev *fbd = s->private;
+
+	return fbnic_dbg_ip_addr_show(s, fbd->ip_dst);
+}
+DEFINE_SHOW_ATTRIBUTE(fbnic_dbg_ip_dst);
+
+static int fbnic_dbg_ipo_src_show(struct seq_file *s, void *v)
+{
+	struct fbnic_dev *fbd = s->private;
+
+	return fbnic_dbg_ip_addr_show(s, fbd->ipo_src);
+}
+DEFINE_SHOW_ATTRIBUTE(fbnic_dbg_ipo_src);
+
+static int fbnic_dbg_ipo_dst_show(struct seq_file *s, void *v)
+{
+	struct fbnic_dev *fbd = s->private;
+
+	return fbnic_dbg_ip_addr_show(s, fbd->ipo_dst);
+}
+DEFINE_SHOW_ATTRIBUTE(fbnic_dbg_ipo_dst);
+
+static void fbnic_dbg_fw_mbx_display(struct seq_file *s,
+				     struct fbnic_dev *fbd, int mbx_idx)
+{
+	struct fbnic_fw_mbx *mbx = &fbd->mbx[mbx_idx];
+	char hdr[80];
+	int i;
+
+	/* Generate header */
+	seq_puts(s, mbx_idx == FBNIC_IPC_MBX_RX_IDX ? "Rx\n" : "Tx\n");
+
+	seq_printf(s, "Rdy: %d Head: %d Tail: %d\n",
+		   mbx->ready, mbx->head, mbx->tail);
+
+	snprintf(hdr, sizeof(hdr), "%3s %-4s %s %-12s %s %-3s %-16s\n",
+		 "Idx", "Len", "E", "Addr", "F", "H", "Raw");
+	seq_puts(s, hdr);
+	fbnic_dbg_desc_break(s, strnlen(hdr, sizeof(hdr)));
+
+	for (i = 0; i < FBNIC_IPC_MBX_DESC_LEN; i++) {
+		u64 desc = __fbnic_mbx_rd_desc(fbd, mbx_idx, i);
+
+		seq_printf(s, "%-3.2d %04lld %d %012llx %d %-3d %016llx\n",
+			   i, FIELD_GET(FBNIC_IPC_MBX_DESC_LEN_MASK, desc),
+			   !!(desc & FBNIC_IPC_MBX_DESC_EOM),
+			   desc & FBNIC_IPC_MBX_DESC_ADDR_MASK,
+			   !!(desc & FBNIC_IPC_MBX_DESC_FW_CMPL),
+			   !!(desc & FBNIC_IPC_MBX_DESC_HOST_CMPL),
+			   desc);
+	}
+}
+
+static int fbnic_dbg_fw_mbx_show(struct seq_file *s, void *v)
+{
+	struct fbnic_dev *fbd = s->private;
+
+	fbnic_dbg_fw_mbx_display(s, fbd, FBNIC_IPC_MBX_RX_IDX);
+
+	/* Add blank line between Rx and Tx */
+	seq_puts(s, "\n");
+
+	fbnic_dbg_fw_mbx_display(s, fbd, FBNIC_IPC_MBX_TX_IDX);
+
+	return 0;
+}
+DEFINE_SHOW_ATTRIBUTE(fbnic_dbg_fw_mbx);
+
+static int fbnic_dbg_fw_log_show(struct seq_file *s, void *v)
+{
+	struct fbnic_dev *fbd = s->private;
+	struct fbnic_fw_log_entry *entry;
+	unsigned long flags;
+
+	if (!fbnic_fw_log_ready(fbd))
+		return -ENXIO;
+
+	spin_lock_irqsave(&fbd->fw_log.lock, flags);
+
+	list_for_each_entry_reverse(entry, &fbd->fw_log.entries, list) {
+		seq_printf(s, FBNIC_FW_LOG_FMT, entry->index,
+			   (entry->timestamp / (MSEC_PER_SEC * 60 * 60 * 24)),
+			   (entry->timestamp / (MSEC_PER_SEC * 60 * 60)) % 24,
+			   ((entry->timestamp / (MSEC_PER_SEC * 60) % 60)),
+			   ((entry->timestamp / MSEC_PER_SEC) % 60),
+			   (entry->timestamp % MSEC_PER_SEC),
+			   entry->msg);
+	}
+
+	spin_unlock_irqrestore(&fbd->fw_log.lock, flags);
+
+	return 0;
+}
+DEFINE_SHOW_ATTRIBUTE(fbnic_dbg_fw_log);
+
+static int fbnic_dbg_pcie_stats_show(struct seq_file *s, void *v)
+{
+	struct fbnic_dev *fbd = s->private;
+
+	rtnl_lock();
+	fbnic_get_hw_stats(fbd);
+
+	seq_printf(s, "ob_rd_tlp: %llu\n", fbd->hw_stats.pcie.ob_rd_tlp.value);
+	seq_printf(s, "ob_rd_dword: %llu\n",
+		   fbd->hw_stats.pcie.ob_rd_dword.value);
+	seq_printf(s, "ob_wr_tlp: %llu\n", fbd->hw_stats.pcie.ob_wr_tlp.value);
+	seq_printf(s, "ob_wr_dword: %llu\n",
+		   fbd->hw_stats.pcie.ob_wr_dword.value);
+	seq_printf(s, "ob_cpl_tlp: %llu\n",
+		   fbd->hw_stats.pcie.ob_cpl_tlp.value);
+	seq_printf(s, "ob_cpl_dword: %llu\n",
+		   fbd->hw_stats.pcie.ob_cpl_dword.value);
+	seq_printf(s, "ob_rd_no_tag: %llu\n",
+		   fbd->hw_stats.pcie.ob_rd_no_tag.value);
+	seq_printf(s, "ob_rd_no_cpl_cred: %llu\n",
+		   fbd->hw_stats.pcie.ob_rd_no_cpl_cred.value);
+	seq_printf(s, "ob_rd_no_np_cred: %llu\n",
+		   fbd->hw_stats.pcie.ob_rd_no_np_cred.value);
+	rtnl_unlock();
+
+	return 0;
+}
+
+DEFINE_SHOW_ATTRIBUTE(fbnic_dbg_pcie_stats);
+
+void fbnic_dbg_fbd_init(struct fbnic_dev *fbd)
+{
+	struct pci_dev *pdev = to_pci_dev(fbd->dev);
+	const char *name = pci_name(pdev);
+
+	fbd->dbg_fbd = debugfs_create_dir(name, fbnic_dbg_root);
+	debugfs_create_file("pcie_stats", 0400, fbd->dbg_fbd, fbd,
+			    &fbnic_dbg_pcie_stats_fops);
+	debugfs_create_file("mac_addr", 0400, fbd->dbg_fbd, fbd,
+			    &fbnic_dbg_mac_addr_fops);
+	debugfs_create_file("tce_tcam", 0400, fbd->dbg_fbd, fbd,
+			    &fbnic_dbg_tce_tcam_fops);
+	debugfs_create_file("act_tcam", 0400, fbd->dbg_fbd, fbd,
+			    &fbnic_dbg_act_tcam_fops);
+	debugfs_create_file("ip_src", 0400, fbd->dbg_fbd, fbd,
+			    &fbnic_dbg_ip_src_fops);
+	debugfs_create_file("ip_dst", 0400, fbd->dbg_fbd, fbd,
+			    &fbnic_dbg_ip_dst_fops);
+	debugfs_create_file("ipo_src", 0400, fbd->dbg_fbd, fbd,
+			    &fbnic_dbg_ipo_src_fops);
+	debugfs_create_file("ipo_dst", 0400, fbd->dbg_fbd, fbd,
+			    &fbnic_dbg_ipo_dst_fops);
+	debugfs_create_file("fw_mbx", 0400, fbd->dbg_fbd, fbd,
+			    &fbnic_dbg_fw_mbx_fops);
+	debugfs_create_file("fw_log", 0400, fbd->dbg_fbd, fbd,
+			    &fbnic_dbg_fw_log_fops);
+}
+
+void fbnic_dbg_fbd_exit(struct fbnic_dev *fbd)
+{
+	debugfs_remove_recursive(fbd->dbg_fbd);
+	fbd->dbg_fbd = NULL;
+}
+
+void fbnic_dbg_init(void)
+{
+	fbnic_dbg_root = debugfs_create_dir(fbnic_driver_name, NULL);
+}
+
+void fbnic_dbg_exit(void)
+{
+	debugfs_remove_recursive(fbnic_dbg_root);
+	fbnic_dbg_root = NULL;
+}

linux-7.2.3/drivers/net/ethernet/meta/fbnic/fbnic_devlink.c

@@ -0,0 +1,669 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) Meta Platforms, Inc. and affiliates. */
+
+#include <linux/unaligned.h>
+#include <linux/pci.h>
+#include <linux/pldmfw.h>
+#include <linux/types.h>
+#include <net/devlink.h>
+
+#include "fbnic.h"
+#include "fbnic_fw.h"
+#include "fbnic_tlv.h"
+
+#define FBNIC_SN_STR_LEN	24
+
+static int fbnic_version_running_put(struct devlink_info_req *req,
+				     struct fbnic_fw_ver *fw_ver,
+				     char *ver_name)
+{
+	char running_ver[FBNIC_FW_VER_MAX_SIZE];
+	int err;
+
+	fbnic_mk_fw_ver_str(fw_ver->version, running_ver);
+	err = devlink_info_version_running_put(req, ver_name, running_ver);
+	if (err)
+		return err;
+
+	if (strlen(fw_ver->commit) > 0) {
+		char commit_name[FBNIC_SN_STR_LEN];
+
+		snprintf(commit_name, FBNIC_SN_STR_LEN, "%s.commit", ver_name);
+		err = devlink_info_version_running_put(req, commit_name,
+						       fw_ver->commit);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
+static int fbnic_version_stored_put(struct devlink_info_req *req,
+				    struct fbnic_fw_ver *fw_ver,
+				    char *ver_name)
+{
+	char stored_ver[FBNIC_FW_VER_MAX_SIZE];
+	int err;
+
+	fbnic_mk_fw_ver_str(fw_ver->version, stored_ver);
+	err = devlink_info_version_stored_put(req, ver_name, stored_ver);
+	if (err)
+		return err;
+
+	if (strlen(fw_ver->commit) > 0) {
+		char commit_name[FBNIC_SN_STR_LEN];
+
+		snprintf(commit_name, FBNIC_SN_STR_LEN, "%s.commit", ver_name);
+		err = devlink_info_version_stored_put(req, commit_name,
+						      fw_ver->commit);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
+static int fbnic_devlink_info_get(struct devlink *devlink,
+				  struct devlink_info_req *req,
+				  struct netlink_ext_ack *extack)
+{
+	struct fbnic_dev *fbd = devlink_priv(devlink);
+	int err;
+
+	err = fbnic_version_running_put(req, &fbd->fw_cap.running.mgmt,
+					DEVLINK_INFO_VERSION_GENERIC_FW);
+	if (err)
+		return err;
+
+	err = fbnic_version_running_put(req, &fbd->fw_cap.running.bootloader,
+					DEVLINK_INFO_VERSION_GENERIC_FW_BOOTLOADER);
+	if (err)
+		return err;
+
+	err = fbnic_version_stored_put(req, &fbd->fw_cap.stored.mgmt,
+				       DEVLINK_INFO_VERSION_GENERIC_FW);
+	if (err)
+		return err;
+
+	err = fbnic_version_stored_put(req, &fbd->fw_cap.stored.bootloader,
+				       DEVLINK_INFO_VERSION_GENERIC_FW_BOOTLOADER);
+	if (err)
+		return err;
+
+	err = fbnic_version_stored_put(req, &fbd->fw_cap.stored.undi,
+				       DEVLINK_INFO_VERSION_GENERIC_FW_UNDI);
+	if (err)
+		return err;
+
+	if (fbd->dsn) {
+		unsigned char serial[FBNIC_SN_STR_LEN];
+		u8 dsn[8];
+
+		put_unaligned_be64(fbd->dsn, dsn);
+		err = snprintf(serial, FBNIC_SN_STR_LEN, "%8phD", dsn);
+		if (err < 0)
+			return err;
+
+		err = devlink_info_serial_number_put(req, serial);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
+static bool
+fbnic_pldm_match_record(struct pldmfw *context, struct pldmfw_record *record)
+{
+	struct pldmfw_desc_tlv *desc;
+	u32 anti_rollback_ver = 0;
+	struct devlink *devlink;
+	struct fbnic_dev *fbd;
+	struct pci_dev *pdev;
+
+	/* First, use the standard PCI matching function */
+	if (!pldmfw_op_pci_match_record(context, record))
+		return false;
+
+	pdev = to_pci_dev(context->dev);
+	fbd = pci_get_drvdata(pdev);
+	devlink = priv_to_devlink(fbd);
+
+	/* If PCI match is successful, check for vendor-specific descriptors */
+	list_for_each_entry(desc, &record->descs, entry) {
+		if (desc->type != PLDM_DESC_ID_VENDOR_DEFINED)
+			continue;
+
+		if (desc->size < 21 || desc->data[0] != 1 ||
+		    desc->data[1] != 15)
+			continue;
+
+		if (memcmp(desc->data + 2, "AntiRollbackVer", 15) != 0)
+			continue;
+
+		anti_rollback_ver = get_unaligned_le32(desc->data + 17);
+		break;
+	}
+
+	/* Compare versions and return error if they do not match */
+	if (anti_rollback_ver < fbd->fw_cap.anti_rollback_version) {
+		char buf[128];
+
+		snprintf(buf, sizeof(buf),
+			 "New firmware anti-rollback version (0x%x) is older than device version (0x%x)!",
+			 anti_rollback_ver, fbd->fw_cap.anti_rollback_version);
+		devlink_flash_update_status_notify(devlink, buf,
+						   "Anti-Rollback", 0, 0);
+
+		return false;
+	}
+
+	return true;
+}
+
+static int
+fbnic_flash_start(struct fbnic_dev *fbd, struct pldmfw_component *component)
+{
+	struct fbnic_fw_completion *cmpl;
+	int err;
+
+	cmpl = fbnic_fw_alloc_cmpl(FBNIC_TLV_MSG_ID_FW_START_UPGRADE_REQ);
+	if (!cmpl)
+		return -ENOMEM;
+
+	err = fbnic_fw_xmit_fw_start_upgrade(fbd, cmpl,
+					     component->identifier,
+					     component->component_size);
+	if (err)
+		goto cmpl_free;
+
+	/* Wait for firmware to ack firmware upgrade start */
+	if (fbnic_mbx_wait_for_cmpl(cmpl))
+		err = cmpl->result;
+	else
+		err = -ETIMEDOUT;
+
+	fbnic_mbx_clear_cmpl(fbd, cmpl);
+cmpl_free:
+	fbnic_fw_put_cmpl(cmpl);
+
+	return err;
+}
+
+static int
+fbnic_flash_component(struct pldmfw *context,
+		      struct pldmfw_component *component)
+{
+	const u8 *data = component->component_data;
+	const u32 size = component->component_size;
+	struct fbnic_fw_completion *cmpl;
+	const char *component_name;
+	struct devlink *devlink;
+	struct fbnic_dev *fbd;
+	struct pci_dev *pdev;
+	u32 offset = 0;
+	u32 length = 0;
+	char buf[32];
+	int err;
+
+	pdev = to_pci_dev(context->dev);
+	fbd = pci_get_drvdata(pdev);
+	devlink = priv_to_devlink(fbd);
+
+	switch (component->identifier) {
+	case QSPI_SECTION_CMRT:
+		component_name = "boot1";
+		break;
+	case QSPI_SECTION_CONTROL_FW:
+		component_name = "boot2";
+		break;
+	case QSPI_SECTION_OPTION_ROM:
+		component_name = "option-rom";
+		break;
+	default:
+		snprintf(buf, sizeof(buf), "Unknown component ID %u!",
+			 component->identifier);
+		devlink_flash_update_status_notify(devlink, buf, NULL, 0,
+						   size);
+		return -EINVAL;
+	}
+
+	/* Once firmware receives the request to start upgrading it responds
+	 * with two messages:
+	 * 1. An ACK that it received the message and possible error code
+	 *    indicating that an upgrade is not currently possible.
+	 * 2. A request for the first chunk of data
+	 *
+	 * Setup completions for write before issuing the start message so
+	 * the driver can catch both messages.
+	 */
+	cmpl = fbnic_fw_alloc_cmpl(FBNIC_TLV_MSG_ID_FW_WRITE_CHUNK_REQ);
+	if (!cmpl)
+		return -ENOMEM;
+
+	err = fbnic_mbx_set_cmpl(fbd, cmpl);
+	if (err)
+		goto cmpl_free;
+
+	devlink_flash_update_timeout_notify(devlink, "Initializing",
+					    component_name, 15);
+	err = fbnic_flash_start(fbd, component);
+	if (err)
+		goto err_no_msg;
+
+	while (offset < size) {
+		if (!fbnic_mbx_wait_for_cmpl(cmpl)) {
+			err = -ETIMEDOUT;
+			break;
+		}
+
+		err = cmpl->result;
+		if (err)
+			break;
+
+		/* Verify firmware is requesting the next chunk in the seq. */
+		if (cmpl->u.fw_update.offset != offset + length) {
+			err = -EFAULT;
+			break;
+		}
+
+		offset = cmpl->u.fw_update.offset;
+		length = cmpl->u.fw_update.length;
+
+		if (length > TLV_MAX_DATA || offset + length > size) {
+			err = -EFAULT;
+			break;
+		}
+
+		devlink_flash_update_status_notify(devlink, "Flashing",
+						   component_name,
+						   offset, size);
+
+		/* Mailbox will set length to 0 once it receives the finish
+		 * message.
+		 */
+		if (!length)
+			continue;
+
+		reinit_completion(&cmpl->done);
+		err = fbnic_fw_xmit_fw_write_chunk(fbd, data, offset, length,
+						   0);
+		if (err)
+			break;
+	}
+
+	if (err) {
+		fbnic_fw_xmit_fw_write_chunk(fbd, NULL, 0, 0, err);
+err_no_msg:
+		snprintf(buf, sizeof(buf), "Mailbox encountered error %d!",
+			 err);
+		devlink_flash_update_status_notify(devlink, buf,
+						   component_name, 0, 0);
+	}
+
+	fbnic_mbx_clear_cmpl(fbd, cmpl);
+cmpl_free:
+	fbnic_fw_put_cmpl(cmpl);
+
+	return err;
+}
+
+static const struct pldmfw_ops fbnic_pldmfw_ops = {
+	.match_record = fbnic_pldm_match_record,
+	.flash_component = fbnic_flash_component,
+};
+
+static int
+fbnic_devlink_flash_update(struct devlink *devlink,
+			   struct devlink_flash_update_params *params,
+			   struct netlink_ext_ack *extack)
+{
+	struct fbnic_dev *fbd = devlink_priv(devlink);
+	const struct firmware *fw = params->fw;
+	struct device *dev = fbd->dev;
+	struct pldmfw context;
+	char *err_msg;
+	int err;
+
+	context.ops = &fbnic_pldmfw_ops;
+	context.dev = dev;
+
+	err = pldmfw_flash_image(&context, fw);
+	if (err) {
+		switch (err) {
+		case -EINVAL:
+			err_msg = "Invalid image";
+			break;
+		case -EOPNOTSUPP:
+			err_msg = "Unsupported image";
+			break;
+		case -ENOMEM:
+			err_msg = "Out of memory";
+			break;
+		case -EFAULT:
+			err_msg = "Invalid header";
+			break;
+		case -ENOENT:
+			err_msg = "No matching record";
+			break;
+		case -ENODEV:
+			err_msg = "No matching device";
+			break;
+		case -ETIMEDOUT:
+			err_msg = "Timed out waiting for reply";
+			break;
+		default:
+			err_msg = "Unknown error";
+			break;
+		}
+
+		NL_SET_ERR_MSG_FMT_MOD(extack,
+				       "Failed to flash PLDM Image: %s (error: %d)",
+				       err_msg, err);
+	}
+
+	return err;
+}
+
+static const struct devlink_ops fbnic_devlink_ops = {
+	.info_get	= fbnic_devlink_info_get,
+	.flash_update	= fbnic_devlink_flash_update,
+};
+
+static int fbnic_fw_reporter_dump(struct devlink_health_reporter *reporter,
+				  struct devlink_fmsg *fmsg, void *priv_ctx,
+				  struct netlink_ext_ack *extack)
+{
+	struct fbnic_dev *fbd = devlink_health_reporter_priv(reporter);
+	u32 offset, index, index_count, length, size;
+	struct fbnic_fw_completion *fw_cmpl;
+	u8 *dump_data, **data;
+	int err;
+
+	fw_cmpl = fbnic_fw_alloc_cmpl(FBNIC_TLV_MSG_ID_COREDUMP_GET_INFO_RESP);
+	if (!fw_cmpl)
+		return -ENOMEM;
+
+	err = fbnic_fw_xmit_coredump_info_msg(fbd, fw_cmpl, true);
+	if (err) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Failed to transmit core dump info msg");
+		goto cmpl_free;
+	}
+	if (!fbnic_mbx_wait_for_cmpl(fw_cmpl)) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Timed out waiting on core dump info");
+		err = -ETIMEDOUT;
+		goto cmpl_cleanup;
+	}
+
+	size = fw_cmpl->u.coredump_info.size;
+	err = fw_cmpl->result;
+
+	fbnic_mbx_clear_cmpl(fbd, fw_cmpl);
+	fbnic_fw_put_cmpl(fw_cmpl);
+
+	/* Handle error returned by firmware */
+	if (err) {
+		NL_SET_ERR_MSG_MOD(extack, "Firmware core dump returned error");
+		return err;
+	}
+	if (!size) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Firmware core dump returned size 0");
+		return -EIO;
+	}
+
+	/* Read the dump, we can only transfer TLV_MAX_DATA at a time */
+	index_count = DIV_ROUND_UP(size, TLV_MAX_DATA);
+
+	fw_cmpl = __fbnic_fw_alloc_cmpl(FBNIC_TLV_MSG_ID_COREDUMP_READ_RESP,
+					sizeof(void *) * index_count + size);
+	if (!fw_cmpl)
+		return -ENOMEM;
+
+	/* Populate pointer table w/ pointer offsets */
+	dump_data = (void *)&fw_cmpl->u.coredump.data[index_count];
+	data = fw_cmpl->u.coredump.data;
+	fw_cmpl->u.coredump.size = size;
+	fw_cmpl->u.coredump.stride = TLV_MAX_DATA;
+
+	for (index = 0; index < index_count; index++) {
+		/* First iteration installs completion */
+		struct fbnic_fw_completion *cmpl_arg = index ? NULL : fw_cmpl;
+
+		offset = index * TLV_MAX_DATA;
+		length = min(size - offset, TLV_MAX_DATA);
+
+		data[index] = dump_data + offset;
+		err = fbnic_fw_xmit_coredump_read_msg(fbd, cmpl_arg,
+						      offset, length);
+		if (err) {
+			NL_SET_ERR_MSG_MOD(extack,
+					   "Failed to transmit core dump msg");
+			if (cmpl_arg)
+				goto cmpl_free;
+			else
+				goto cmpl_cleanup;
+		}
+
+		if (fbnic_mbx_wait_for_cmpl(fw_cmpl)) {
+			reinit_completion(&fw_cmpl->done);
+		} else {
+			NL_SET_ERR_MSG_FMT_MOD(extack,
+					       "Timed out waiting on core dump (%d/%d)",
+					       index + 1, index_count);
+			err = -ETIMEDOUT;
+			goto cmpl_cleanup;
+		}
+
+		/* If we didn't see the reply record as incomplete */
+		if (fw_cmpl->u.coredump.data[index]) {
+			NL_SET_ERR_MSG_FMT_MOD(extack,
+					       "No data for core dump chunk (%d/%d)",
+					       index + 1, index_count);
+			err = -EIO;
+			goto cmpl_cleanup;
+		}
+	}
+
+	devlink_fmsg_binary_pair_nest_start(fmsg, "FW coredump");
+
+	for (offset = 0; offset < size; offset += length) {
+		length = min_t(u32, size - offset, TLV_MAX_DATA);
+
+		devlink_fmsg_binary_put(fmsg, dump_data + offset, length);
+	}
+
+	devlink_fmsg_binary_pair_nest_end(fmsg);
+
+cmpl_cleanup:
+	fbnic_mbx_clear_cmpl(fbd, fw_cmpl);
+cmpl_free:
+	fbnic_fw_put_cmpl(fw_cmpl);
+
+	return err;
+}
+
+static int
+fbnic_fw_reporter_diagnose(struct devlink_health_reporter *reporter,
+			   struct devlink_fmsg *fmsg,
+			   struct netlink_ext_ack *extack)
+{
+	struct fbnic_dev *fbd = devlink_health_reporter_priv(reporter);
+	u32 sec, msec;
+
+	/* Device is most likely down, we're not exchanging heartbeats */
+	if (!fbd->prev_firmware_time)
+		return 0;
+
+	sec = div_u64_rem(fbd->firmware_time, MSEC_PER_SEC, &msec);
+
+	devlink_fmsg_pair_nest_start(fmsg, "last_heartbeat");
+	devlink_fmsg_obj_nest_start(fmsg);
+	devlink_fmsg_pair_nest_start(fmsg, "fw_uptime");
+	devlink_fmsg_obj_nest_start(fmsg);
+	devlink_fmsg_u32_pair_put(fmsg, "sec", sec);
+	devlink_fmsg_u32_pair_put(fmsg, "msec", msec);
+	devlink_fmsg_obj_nest_end(fmsg);
+	devlink_fmsg_pair_nest_end(fmsg);
+	devlink_fmsg_obj_nest_end(fmsg);
+	devlink_fmsg_pair_nest_end(fmsg);
+
+	return 0;
+}
+
+void __printf(2, 3)
+fbnic_devlink_fw_report(struct fbnic_dev *fbd, const char *format, ...)
+{
+	char msg[FBNIC_FW_LOG_MAX_SIZE];
+	va_list args;
+
+	va_start(args, format);
+	vsnprintf(msg, FBNIC_FW_LOG_MAX_SIZE, format, args);
+	va_end(args);
+
+	devlink_health_report(fbd->fw_reporter, msg, fbd);
+	if (fbnic_fw_log_ready(fbd))
+		fbnic_fw_log_write(fbd, 0, fbd->firmware_time, msg);
+}
+
+static const struct devlink_health_reporter_ops fbnic_fw_ops = {
+	.name = "fw",
+	.dump = fbnic_fw_reporter_dump,
+	.diagnose = fbnic_fw_reporter_diagnose,
+};
+
+static u32 fbnic_read_otp_status(struct fbnic_dev *fbd)
+{
+	return fbnic_fw_rd32(fbd, FBNIC_NS_OTP_STATUS);
+}
+
+static int
+fbnic_otp_reporter_dump(struct devlink_health_reporter *reporter,
+			struct devlink_fmsg *fmsg, void *priv_ctx,
+			struct netlink_ext_ack *extack)
+{
+	struct fbnic_dev *fbd = devlink_health_reporter_priv(reporter);
+	u32 otp_status, otp_write_status, m;
+
+	otp_status = fbnic_read_otp_status(fbd);
+	otp_write_status = fbnic_fw_rd32(fbd, FBNIC_NS_OTP_WRITE_STATUS);
+
+	/* Dump OTP status */
+	devlink_fmsg_pair_nest_start(fmsg, "OTP");
+	devlink_fmsg_obj_nest_start(fmsg);
+
+	devlink_fmsg_u32_pair_put(fmsg, "Status", otp_status);
+
+	/* Extract OTP Write Data status */
+	m = FBNIC_NS_OTP_WRITE_DATA_STATUS_MASK;
+	devlink_fmsg_u32_pair_put(fmsg, "Data",
+				  FIELD_GET(m, otp_write_status));
+
+	/* Extract OTP Write ECC status */
+	m = FBNIC_NS_OTP_WRITE_ECC_STATUS_MASK;
+	devlink_fmsg_u32_pair_put(fmsg, "ECC",
+				  FIELD_GET(m, otp_write_status));
+
+	devlink_fmsg_obj_nest_end(fmsg);
+	devlink_fmsg_pair_nest_end(fmsg);
+
+	return 0;
+}
+
+void fbnic_devlink_otp_check(struct fbnic_dev *fbd, const char *msg)
+{
+	/* Check if there is anything to report */
+	if (!fbnic_read_otp_status(fbd))
+		return;
+
+	devlink_health_report(fbd->otp_reporter, msg, fbd);
+	if (fbnic_fw_log_ready(fbd))
+		fbnic_fw_log_write(fbd, 0, fbd->firmware_time, msg);
+}
+
+static const struct devlink_health_reporter_ops fbnic_otp_ops = {
+	.name = "otp",
+	.dump = fbnic_otp_reporter_dump,
+};
+
+int fbnic_devlink_health_create(struct fbnic_dev *fbd)
+{
+	fbd->fw_reporter = devlink_health_reporter_create(priv_to_devlink(fbd),
+							  &fbnic_fw_ops, fbd);
+	if (IS_ERR(fbd->fw_reporter)) {
+		dev_warn(fbd->dev,
+			 "Failed to create FW fault reporter: %pe\n",
+			 fbd->fw_reporter);
+		return PTR_ERR(fbd->fw_reporter);
+	}
+
+	fbd->otp_reporter = devlink_health_reporter_create(priv_to_devlink(fbd),
+							   &fbnic_otp_ops, fbd);
+	if (IS_ERR(fbd->otp_reporter)) {
+		devlink_health_reporter_destroy(fbd->fw_reporter);
+		dev_warn(fbd->dev,
+			 "Failed to create OTP fault reporter: %pe\n",
+			 fbd->otp_reporter);
+		return PTR_ERR(fbd->otp_reporter);
+	}
+
+	return 0;
+}
+
+void fbnic_devlink_health_destroy(struct fbnic_dev *fbd)
+{
+	devlink_health_reporter_destroy(fbd->otp_reporter);
+	devlink_health_reporter_destroy(fbd->fw_reporter);
+}
+
+void fbnic_devlink_free(struct fbnic_dev *fbd)
+{
+	struct devlink *devlink = priv_to_devlink(fbd);
+
+	devlink_free(devlink);
+}
+
+struct fbnic_dev *fbnic_devlink_alloc(struct pci_dev *pdev)
+{
+	void __iomem * const *iomap_table;
+	struct devlink *devlink;
+	struct fbnic_dev *fbd;
+
+	devlink = devlink_alloc(&fbnic_devlink_ops, sizeof(struct fbnic_dev),
+				&pdev->dev);
+	if (!devlink)
+		return NULL;
+
+	fbd = devlink_priv(devlink);
+	pci_set_drvdata(pdev, fbd);
+	fbd->dev = &pdev->dev;
+
+	iomap_table = pcim_iomap_table(pdev);
+	fbd->uc_addr0 = iomap_table[0];
+	fbd->uc_addr4 = iomap_table[4];
+
+	fbd->dsn = pci_get_dsn(pdev);
+	fbd->mps = pcie_get_mps(pdev);
+	fbd->readrq = pcie_get_readrq(pdev);
+	fbd->relaxed_ord = pcie_relaxed_ordering_enabled(pdev);
+
+	fbd->mac_addr_boundary = FBNIC_RPC_TCAM_MACDA_DEFAULT_BOUNDARY;
+
+	return fbd;
+}
+
+void fbnic_devlink_register(struct fbnic_dev *fbd)
+{
+	struct devlink *devlink = priv_to_devlink(fbd);
+
+	devlink_register(devlink);
+}
+
+void fbnic_devlink_unregister(struct fbnic_dev *fbd)
+{
+	struct devlink *devlink = priv_to_devlink(fbd);
+
+	devlink_unregister(devlink);
+}

linux-7.2.3/drivers/net/ethernet/meta/fbnic/fbnic_drvinfo.h

@@ -0,0 +1,5 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) Meta Platforms, Inc. and affiliates. */
+
+#define DRV_NAME "fbnic"
+#define DRV_SUMMARY "Meta(R) Host Network Interface Driver"

linux-7.2.3/drivers/net/ethernet/meta/fbnic/fbnic_fw.h

@@ -0,0 +1,363 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) Meta Platforms, Inc. and affiliates. */
+
+#ifndef _FBNIC_FW_H_
+#define _FBNIC_FW_H_
+
+#include <linux/completion.h>
+#include <linux/if_ether.h>
+#include <linux/types.h>
+
+struct fbnic_dev;
+struct fbnic_tlv_msg;
+
+struct fbnic_fw_mbx {
+	u8 ready, head, tail;
+	struct {
+		struct fbnic_tlv_msg	*msg;
+		dma_addr_t		addr;
+	} buf_info[FBNIC_IPC_MBX_DESC_LEN];
+};
+
+// FW_VER_MAX_SIZE must match ETHTOOL_FWVERS_LEN
+#define FBNIC_FW_VER_MAX_SIZE			32
+// Formatted version is in the format XX.YY.ZZ_RRR_COMMIT
+#define FBNIC_FW_CAP_RESP_COMMIT_MAX_SIZE	(FBNIC_FW_VER_MAX_SIZE - 13)
+#define FBNIC_FW_LOG_VERSION			1
+#define FBNIC_FW_LOG_MAX_SIZE			256
+/*
+ * The max amount of logs which can fit in a single mailbox message. Firmware
+ * assumes each mailbox message is 4096B. The amount of messages supported is
+ * calculated as 4096 minus headers for message, arrays, and length minus the
+ * size of length divided by headers for each array plus the maximum LOG size,
+ * and the size of MSEC and INDEX. Put another way:
+ *
+ * MAX_LOG_HISTORY = ((4096 - TLV_HDR_SZ * 5 - LENGTH_SZ)
+ *                    / (FBNIC_FW_LOG_MAX_SIZE + TLV_HDR_SZ * 3 + MSEC_SZ
+ *                       + INDEX_SZ))
+ */
+#define FBNIC_FW_MAX_LOG_HISTORY		14
+#define FBNIC_MBX_RX_TO_SEC			10
+
+struct fbnic_fw_ver {
+	u32 version;
+	char commit[FBNIC_FW_CAP_RESP_COMMIT_MAX_SIZE];
+};
+
+struct fbnic_fw_cap {
+	struct {
+		struct fbnic_fw_ver mgmt, bootloader;
+	} running;
+	struct {
+		struct fbnic_fw_ver mgmt, bootloader, undi;
+	} stored;
+	u8	active_slot;
+	u8	bmc_mac_addr[4][ETH_ALEN];
+	u8	bmc_present		: 1;
+	u8	need_bmc_tcam_reinit	: 1;
+	u8	need_bmc_macda_sync	: 1;
+	u8	all_multi		: 1;
+	u8	link_speed;
+	u8	link_fec;
+	u32	anti_rollback_version;
+};
+
+struct fbnic_fw_completion {
+	u32 msg_type;
+	struct completion done;
+	struct kref ref_count;
+	int result;
+	union {
+		struct {
+			u32 size;
+		} coredump_info;
+		struct {
+			u32 size;
+			u16 stride;
+			u8 *data[];
+		} coredump;
+		struct {
+			u32 offset;
+			u32 length;
+		} fw_update;
+		struct {
+			u16 length;
+			u8 offset;
+			u8 page;
+			u8 bank;
+			u8 data[] __aligned(sizeof(u32)) __counted_by(length);
+		} qsfp;
+		struct {
+			s32 millivolts;
+			s32 millidegrees;
+		} tsene;
+	} u;
+};
+
+u64 __fbnic_mbx_rd_desc(struct fbnic_dev *fbd, int mbx_idx, int desc_idx);
+void fbnic_mbx_init(struct fbnic_dev *fbd);
+void fbnic_mbx_clean(struct fbnic_dev *fbd);
+int fbnic_mbx_set_cmpl(struct fbnic_dev *fbd,
+		       struct fbnic_fw_completion *cmpl_data);
+void fbnic_mbx_clear_cmpl(struct fbnic_dev *fbd,
+			  struct fbnic_fw_completion *cmpl_data);
+void fbnic_mbx_poll(struct fbnic_dev *fbd);
+int fbnic_mbx_poll_tx_ready(struct fbnic_dev *fbd);
+void fbnic_mbx_flush_tx(struct fbnic_dev *fbd);
+
+/**
+ * enum fbnic_fw_self_test_codes - return codes from self test routines
+ *
+ * These are the codes returned from the self test routines and
+ * stored in the test result array indexed by the specific
+ * test name.
+ *
+ * @FBNIC_TEST_FW_SUCCESS: test success
+ * @FBNIC_TEST_FW_NO_FIRMWARE: FW interface not present
+ * @FBNIC_TEST_FW_NO_CMPL: No completion available
+ * @FBNIC_TEST_FW_NO_XMIT: Could not xmit message
+ * @FBNIC_TEST_FW_NO_MSG: no message returned
+ * @FBNIC_TEST_FW_PARSE: returned message had parsing error
+ */
+enum fbnic_fw_self_test_codes {
+	FBNIC_TEST_FW_SUCCESS = 0,
+	FBNIC_TEST_FW_NO_FIRMWARE = 10,
+	FBNIC_TEST_FW_NO_CMPL = 20,
+	FBNIC_TEST_FW_NO_XMIT = 30,
+	FBNIC_TEST_FW_NO_MSG = 40,
+	FBNIC_TEST_FW_PARSE = 50,
+};
+
+enum fbnic_fw_self_test_codes fbnic_fw_mbx_self_test(struct fbnic_dev *fbd);
+int fbnic_fw_xmit_test_msg(struct fbnic_dev *fbd,
+			   struct fbnic_fw_completion *c);
+int fbnic_fw_xmit_ownership_msg(struct fbnic_dev *fbd, bool take_ownership);
+int fbnic_fw_init_heartbeat(struct fbnic_dev *fbd, bool poll);
+void fbnic_fw_check_heartbeat(struct fbnic_dev *fbd);
+int fbnic_fw_xmit_coredump_info_msg(struct fbnic_dev *fbd,
+				    struct fbnic_fw_completion *cmpl_data,
+				    bool force);
+int fbnic_fw_xmit_coredump_read_msg(struct fbnic_dev *fbd,
+				    struct fbnic_fw_completion *cmpl_data,
+				    u32 offset, u32 length);
+int fbnic_fw_xmit_fw_start_upgrade(struct fbnic_dev *fbd,
+				   struct fbnic_fw_completion *cmpl_data,
+				   unsigned int id, unsigned int len);
+int fbnic_fw_xmit_fw_write_chunk(struct fbnic_dev *fbd,
+				 const u8 *data, u32 offset, u16 length,
+				 int cancel_error);
+int fbnic_fw_xmit_qsfp_read_msg(struct fbnic_dev *fbd,
+				struct fbnic_fw_completion *cmpl_data,
+				u32 page, u32 bank, u32 offset, u32 length);
+int fbnic_fw_xmit_tsene_read_msg(struct fbnic_dev *fbd,
+				 struct fbnic_fw_completion *cmpl_data);
+int fbnic_fw_xmit_send_logs(struct fbnic_dev *fbd, bool enable,
+			    bool send_log_history);
+int fbnic_fw_xmit_rpc_macda_sync(struct fbnic_dev *fbd);
+struct fbnic_fw_completion *__fbnic_fw_alloc_cmpl(u32 msg_type,
+						  size_t priv_size);
+struct fbnic_fw_completion *fbnic_fw_alloc_cmpl(u32 msg_type);
+void fbnic_fw_put_cmpl(struct fbnic_fw_completion *cmpl_data);
+
+static inline unsigned long
+fbnic_mbx_wait_for_cmpl(struct fbnic_fw_completion *cmpl)
+{
+	return wait_for_completion_timeout(&cmpl->done,
+					   FBNIC_MBX_RX_TO_SEC * HZ);
+}
+
+#define fbnic_mk_full_fw_ver_str(_rev_id, _delim, _commit, _str, _str_sz) \
+do {									\
+	const u32 __rev_id = _rev_id;					\
+	snprintf(_str, _str_sz, "%02lu.%02lu.%02lu-%03lu%s%s",	\
+		 FIELD_GET(FBNIC_FW_CAP_RESP_VERSION_MAJOR, __rev_id),	\
+		 FIELD_GET(FBNIC_FW_CAP_RESP_VERSION_MINOR, __rev_id),	\
+		 FIELD_GET(FBNIC_FW_CAP_RESP_VERSION_PATCH, __rev_id),	\
+		 FIELD_GET(FBNIC_FW_CAP_RESP_VERSION_BUILD, __rev_id),	\
+		 _delim, _commit);					\
+} while (0)
+
+#define fbnic_mk_fw_ver_str(_rev_id, _str) \
+	fbnic_mk_full_fw_ver_str(_rev_id, "", "", _str, sizeof(_str))
+
+enum {
+	QSPI_SECTION_CMRT			= 0,
+	QSPI_SECTION_CONTROL_FW			= 1,
+	QSPI_SECTION_UCODE			= 2,
+	QSPI_SECTION_OPTION_ROM			= 3,
+	QSPI_SECTION_USER			= 4,
+	QSPI_SECTION_INVALID,
+};
+
+#define FW_HEARTBEAT_PERIOD		(10 * HZ)
+
+enum {
+	FBNIC_TLV_MSG_ID_HOST_CAP_REQ			= 0x10,
+	FBNIC_TLV_MSG_ID_FW_CAP_RESP			= 0x11,
+	FBNIC_TLV_MSG_ID_OWNERSHIP_REQ			= 0x12,
+	FBNIC_TLV_MSG_ID_OWNERSHIP_RESP			= 0x13,
+	FBNIC_TLV_MSG_ID_HEARTBEAT_REQ			= 0x14,
+	FBNIC_TLV_MSG_ID_HEARTBEAT_RESP			= 0x15,
+	FBNIC_TLV_MSG_ID_COREDUMP_GET_INFO_REQ		= 0x18,
+	FBNIC_TLV_MSG_ID_COREDUMP_GET_INFO_RESP		= 0x19,
+	FBNIC_TLV_MSG_ID_COREDUMP_READ_REQ		= 0x20,
+	FBNIC_TLV_MSG_ID_COREDUMP_READ_RESP		= 0x21,
+	FBNIC_TLV_MSG_ID_FW_START_UPGRADE_REQ		= 0x22,
+	FBNIC_TLV_MSG_ID_FW_START_UPGRADE_RESP		= 0x23,
+	FBNIC_TLV_MSG_ID_FW_WRITE_CHUNK_REQ		= 0x24,
+	FBNIC_TLV_MSG_ID_FW_WRITE_CHUNK_RESP		= 0x25,
+	FBNIC_TLV_MSG_ID_FW_FINISH_UPGRADE_REQ		= 0x28,
+	FBNIC_TLV_MSG_ID_FW_FINISH_UPGRADE_RESP		= 0x29,
+	FBNIC_TLV_MSG_ID_QSFP_READ_REQ			= 0x38,
+	FBNIC_TLV_MSG_ID_QSFP_READ_RESP			= 0x39,
+	FBNIC_TLV_MSG_ID_TSENE_READ_REQ			= 0x3C,
+	FBNIC_TLV_MSG_ID_TSENE_READ_RESP		= 0x3D,
+	FBNIC_TLV_MSG_ID_LOG_SEND_LOGS_REQ		= 0x43,
+	FBNIC_TLV_MSG_ID_LOG_MSG_REQ			= 0x44,
+	FBNIC_TLV_MSG_ID_LOG_MSG_RESP			= 0x45,
+	FBNIC_TLV_MSG_ID_RPC_MAC_SYNC_REQ		= 0x46,
+};
+
+#define FBNIC_FW_CAP_RESP_VERSION_MAJOR		CSR_GENMASK(31, 24)
+#define FBNIC_FW_CAP_RESP_VERSION_MINOR		CSR_GENMASK(23, 16)
+#define FBNIC_FW_CAP_RESP_VERSION_PATCH		CSR_GENMASK(15, 8)
+#define FBNIC_FW_CAP_RESP_VERSION_BUILD		CSR_GENMASK(7, 0)
+enum {
+	FBNIC_FW_CAP_RESP_VERSION			= 0x0,
+	FBNIC_FW_CAP_RESP_BMC_PRESENT			= 0x1,
+	FBNIC_FW_CAP_RESP_BMC_MAC_ADDR			= 0x2,
+	FBNIC_FW_CAP_RESP_BMC_MAC_ARRAY			= 0x3,
+	FBNIC_FW_CAP_RESP_STORED_VERSION		= 0x4,
+	FBNIC_FW_CAP_RESP_ACTIVE_FW_SLOT		= 0x5,
+	FBNIC_FW_CAP_RESP_VERSION_COMMIT_STR		= 0x6,
+	FBNIC_FW_CAP_RESP_BMC_ALL_MULTI			= 0x8,
+	FBNIC_FW_CAP_RESP_FW_STATE			= 0x9,
+	FBNIC_FW_CAP_RESP_FW_LINK_SPEED			= 0xa,
+	FBNIC_FW_CAP_RESP_FW_LINK_FEC			= 0xb,
+	FBNIC_FW_CAP_RESP_STORED_COMMIT_STR		= 0xc,
+	FBNIC_FW_CAP_RESP_CMRT_VERSION			= 0xd,
+	FBNIC_FW_CAP_RESP_STORED_CMRT_VERSION		= 0xe,
+	FBNIC_FW_CAP_RESP_CMRT_COMMIT_STR		= 0xf,
+	FBNIC_FW_CAP_RESP_STORED_CMRT_COMMIT_STR	= 0x10,
+	FBNIC_FW_CAP_RESP_UEFI_VERSION			= 0x11,
+	FBNIC_FW_CAP_RESP_UEFI_COMMIT_STR		= 0x12,
+	FBNIC_FW_CAP_RESP_ANTI_ROLLBACK_VERSION		= 0x15,
+	FBNIC_FW_CAP_RESP_MSG_MAX
+};
+
+enum {
+	FBNIC_FW_LINK_MODE_25CR			= 1,
+	FBNIC_FW_LINK_MODE_50CR2		= 2,
+	FBNIC_FW_LINK_MODE_50CR			= 3,
+	FBNIC_FW_LINK_MODE_100CR2		= 4,
+};
+
+enum {
+	FBNIC_FW_LINK_FEC_NONE			= 1,
+	FBNIC_FW_LINK_FEC_RS			= 2,
+	FBNIC_FW_LINK_FEC_BASER			= 3,
+};
+
+enum {
+	FBNIC_FW_QSFP_BANK			= 0x0,
+	FBNIC_FW_QSFP_PAGE			= 0x1,
+	FBNIC_FW_QSFP_OFFSET			= 0x2,
+	FBNIC_FW_QSFP_LENGTH			= 0x3,
+	FBNIC_FW_QSFP_ERROR			= 0x4,
+	FBNIC_FW_QSFP_DATA			= 0x5,
+	FBNIC_FW_QSFP_MSG_MAX
+};
+
+enum {
+	FBNIC_FW_TSENE_THERM			= 0x0,
+	FBNIC_FW_TSENE_VOLT			= 0x1,
+	FBNIC_FW_TSENE_ERROR			= 0x2,
+	FBNIC_FW_TSENE_MSG_MAX
+};
+
+enum {
+	FBNIC_FW_OWNERSHIP_FLAG			= 0x0,
+	FBNIC_FW_OWNERSHIP_TIME			= 0x1,
+	FBNIC_FW_OWNERSHIP_MSG_MAX
+};
+
+enum {
+	FBNIC_FW_HEARTBEAT_UPTIME               = 0x0,
+	FBNIC_FW_HEARTBEAT_NUMBER_OF_MESSAGES   = 0x1,
+	FBNIC_FW_HEARTBEAT_MSG_MAX
+};
+
+enum {
+	FBNIC_FW_COREDUMP_REQ_INFO_CREATE	= 0x0,
+	FBNIC_FW_COREDUMP_REQ_INFO_MSG_MAX
+};
+
+enum {
+	FBNIC_FW_COREDUMP_INFO_AVAILABLE	= 0x0,
+	FBNIC_FW_COREDUMP_INFO_SIZE		= 0x1,
+	FBNIC_FW_COREDUMP_INFO_ERROR		= 0x2,
+	FBNIC_FW_COREDUMP_INFO_MSG_MAX
+};
+
+enum {
+	FBNIC_FW_COREDUMP_READ_OFFSET		= 0x0,
+	FBNIC_FW_COREDUMP_READ_LENGTH		= 0x1,
+	FBNIC_FW_COREDUMP_READ_DATA		= 0x2,
+	FBNIC_FW_COREDUMP_READ_ERROR		= 0x3,
+	FBNIC_FW_COREDUMP_READ_MSG_MAX
+};
+
+enum {
+	FBNIC_FW_START_UPGRADE_ERROR		= 0x0,
+	FBNIC_FW_START_UPGRADE_SECTION		= 0x1,
+	FBNIC_FW_START_UPGRADE_IMAGE_LENGTH	= 0x2,
+	FBNIC_FW_START_UPGRADE_MSG_MAX
+};
+
+enum {
+	FBNIC_FW_WRITE_CHUNK_OFFSET		= 0x0,
+	FBNIC_FW_WRITE_CHUNK_LENGTH		= 0x1,
+	FBNIC_FW_WRITE_CHUNK_DATA		= 0x2,
+	FBNIC_FW_WRITE_CHUNK_ERROR		= 0x3,
+	FBNIC_FW_WRITE_CHUNK_MSG_MAX
+};
+
+enum {
+	FBNIC_FW_FINISH_UPGRADE_ERROR		= 0x0,
+	FBNIC_FW_FINISH_UPGRADE_MSG_MAX
+};
+
+enum {
+	FBNIC_SEND_LOGS				= 0x0,
+	FBNIC_SEND_LOGS_VERSION			= 0x1,
+	FBNIC_SEND_LOGS_HISTORY			= 0x2,
+	FBNIC_SEND_LOGS_MSG_MAX
+};
+
+enum {
+	FBNIC_FW_LOG_MSEC			= 0x0,
+	FBNIC_FW_LOG_INDEX			= 0x1,
+	FBNIC_FW_LOG_MSG			= 0x2,
+	FBNIC_FW_LOG_LENGTH			= 0x3,
+	FBNIC_FW_LOG_MSEC_ARRAY			= 0x4,
+	FBNIC_FW_LOG_INDEX_ARRAY		= 0x5,
+	FBNIC_FW_LOG_MSG_ARRAY			= 0x6,
+	FBNIC_FW_LOG_MSG_MAX
+};
+
+enum {
+	FBNIC_FW_RPC_MAC_SYNC_RX_FLAGS		= 0x0,
+	FBNIC_FW_RPC_MAC_SYNC_UC_ARRAY		= 0x1,
+	FBNIC_FW_RPC_MAC_SYNC_MC_ARRAY		= 0x2,
+	FBNIC_FW_RPC_MAC_SYNC_MAC_ADDR		= 0x3,
+	FBNIC_FW_RPC_MAC_SYNC_MSG_MAX
+};
+
+#define FW_RPC_MAC_SYNC_RX_FLAGS_PROMISC	1
+#define FW_RPC_MAC_SYNC_RX_FLAGS_ALLMULTI	2
+#define FW_RPC_MAC_SYNC_RX_FLAGS_BROADCAST	4
+
+#define FW_RPC_MAC_SYNC_UC_ARRAY_SIZE		8
+#define FW_RPC_MAC_SYNC_MC_ARRAY_SIZE		8
+
+#endif /* _FBNIC_FW_H_ */

linux-7.2.3/drivers/net/ethernet/meta/fbnic/fbnic_fw_log.c

@@ -0,0 +1,120 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) Meta Platforms, Inc. and affiliates. */
+
+#include <linux/spinlock.h>
+#include <linux/vmalloc.h>
+
+#include "fbnic.h"
+#include "fbnic_fw.h"
+#include "fbnic_fw_log.h"
+
+void fbnic_fw_log_enable(struct fbnic_dev *fbd, bool send_hist)
+{
+	int err;
+
+	if (!fbnic_fw_log_ready(fbd))
+		return;
+
+	if (fbd->fw_cap.running.mgmt.version < MIN_FW_VER_CODE_HIST)
+		send_hist = false;
+
+	err = fbnic_fw_xmit_send_logs(fbd, true, send_hist);
+	if (err && err != -EOPNOTSUPP)
+		dev_warn(fbd->dev, "Unable to enable firmware logs: %d\n", err);
+}
+
+void fbnic_fw_log_disable(struct fbnic_dev *fbd)
+{
+	int err;
+
+	err = fbnic_fw_xmit_send_logs(fbd, false, false);
+	if (err && err != -EOPNOTSUPP)
+		dev_warn(fbd->dev, "Unable to disable firmware logs: %d\n",
+			 err);
+}
+
+int fbnic_fw_log_init(struct fbnic_dev *fbd)
+{
+	struct fbnic_fw_log *log = &fbd->fw_log;
+	void *data;
+
+	if (WARN_ON_ONCE(fbnic_fw_log_ready(fbd)))
+		return -EEXIST;
+
+	data = vmalloc(FBNIC_FW_LOG_SIZE);
+	if (!data)
+		return -ENOMEM;
+
+	spin_lock_init(&fbd->fw_log.lock);
+	INIT_LIST_HEAD(&log->entries);
+	log->size = FBNIC_FW_LOG_SIZE;
+	log->data_start = data;
+	log->data_end = data + FBNIC_FW_LOG_SIZE;
+
+	return 0;
+}
+
+void fbnic_fw_log_free(struct fbnic_dev *fbd)
+{
+	struct fbnic_fw_log *log = &fbd->fw_log;
+
+	if (!fbnic_fw_log_ready(fbd))
+		return;
+
+	INIT_LIST_HEAD(&log->entries);
+	log->size = 0;
+	vfree(log->data_start);
+	log->data_start = NULL;
+	log->data_end = NULL;
+}
+
+int fbnic_fw_log_write(struct fbnic_dev *fbd, u64 index, u32 timestamp,
+		       const char *msg)
+{
+	struct fbnic_fw_log_entry *entry, *head, *tail, *next;
+	struct fbnic_fw_log *log = &fbd->fw_log;
+	size_t msg_len = strlen(msg) + 1;
+	unsigned long flags;
+	void *entry_end;
+
+	if (!fbnic_fw_log_ready(fbd)) {
+		dev_err(fbd->dev, "Firmware sent log entry without being requested!\n");
+		return -ENOSPC;
+	}
+
+	spin_lock_irqsave(&log->lock, flags);
+
+	if (list_empty(&log->entries)) {
+		entry = log->data_start;
+	} else {
+		head = list_first_entry(&log->entries, typeof(*head), list);
+		entry_end = head->msg + head->len + 1;
+		entry = PTR_ALIGN(entry_end, 8);
+	}
+
+	entry_end = entry->msg + msg_len + 1;
+
+	/* We've reached the end of the buffer, wrap around */
+	if (entry_end > log->data_end) {
+		entry = log->data_start;
+		entry_end = entry->msg + msg_len + 1;
+	}
+
+	/* Make room for entry by removing from tail. */
+	list_for_each_entry_safe_reverse(tail, next, &log->entries, list) {
+		if (entry <= tail && entry_end > (void *)tail)
+			list_del(&tail->list);
+		else
+			break;
+	}
+
+	entry->index = index;
+	entry->timestamp = timestamp;
+	entry->len = msg_len;
+	strscpy(entry->msg, msg, entry->len);
+	list_add(&entry->list, &log->entries);
+
+	spin_unlock_irqrestore(&log->lock, flags);
+
+	return 0;
+}

linux-7.2.3/drivers/net/ethernet/meta/fbnic/fbnic_fw_log.h

@@ -0,0 +1,45 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) Meta Platforms, Inc. and affiliates. */
+
+#ifndef _FBNIC_FW_LOG_H_
+#define _FBNIC_FW_LOG_H_
+
+#include <linux/spinlock.h>
+#include <linux/types.h>
+
+/* A 512K log buffer was chosen fairly arbitrarily */
+#define FBNIC_FW_LOG_SIZE	(512 * 1024) /* bytes */
+
+/* Firmware log output is prepended with log index followed by a timestamp.
+ * The timestamp is similar to Zephyr's format DD:HH:MM:SS.MMM
+ */
+#define FBNIC_FW_LOG_FMT	"[%5lld] [%02ld:%02ld:%02ld:%02ld.%03ld] %s\n"
+
+struct fbnic_dev;
+
+struct fbnic_fw_log_entry {
+	struct list_head	list;
+	u64			index;
+	u32			timestamp;
+	u16			len;
+	char			msg[] __counted_by(len);
+};
+
+struct fbnic_fw_log {
+	void			*data_start;
+	void			*data_end;
+	size_t			size;
+	struct list_head	entries;
+	/* Spin lock for accessing or modifying entries */
+	spinlock_t		lock;
+};
+
+#define fbnic_fw_log_ready(_fbd)	(!!(_fbd)->fw_log.data_start)
+
+void fbnic_fw_log_enable(struct fbnic_dev *fbd, bool send_hist);
+void fbnic_fw_log_disable(struct fbnic_dev *fbd);
+int fbnic_fw_log_init(struct fbnic_dev *fbd);
+void fbnic_fw_log_free(struct fbnic_dev *fbd);
+int fbnic_fw_log_write(struct fbnic_dev *fbd, u64 index, u32 timestamp,
+		       const char *msg);
+#endif /* _FBNIC_FW_LOG_H_ */

linux-7.2.3/drivers/net/ethernet/meta/fbnic/fbnic_hw_stats.c

@@ -0,0 +1,601 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) Meta Platforms, Inc. and affiliates. */
+
+#include <linux/rtnetlink.h>
+
+#include "fbnic.h"
+
+static void fbnic_hw_stat_rst32(struct fbnic_dev *fbd, u32 reg,
+				struct fbnic_stat_counter *stat)
+{
+	/* We do not touch the "value" field here.
+	 * It gets zeroed out on fbd structure allocation.
+	 * After that we want it to grow continuously
+	 * through device resets and power state changes.
+	 */
+	stat->u.old_reg_value_32 = rd32(fbd, reg);
+}
+
+static void fbnic_hw_stat_rd32(struct fbnic_dev *fbd, u32 reg,
+			       struct fbnic_stat_counter *stat)
+{
+	u32 new_reg_value;
+
+	new_reg_value = rd32(fbd, reg);
+	stat->value += new_reg_value - stat->u.old_reg_value_32;
+	stat->u.old_reg_value_32 = new_reg_value;
+}
+
+u64 fbnic_stat_rd64(struct fbnic_dev *fbd, u32 reg, u32 offset)
+{
+	u32 prev_upper, upper, lower, diff;
+
+	prev_upper = rd32(fbd, reg + offset);
+	lower = rd32(fbd, reg);
+	upper = rd32(fbd, reg + offset);
+
+	diff = upper - prev_upper;
+	if (!diff)
+		return ((u64)upper << 32) | lower;
+
+	if (diff > 1)
+		dev_warn_once(fbd->dev,
+			      "Stats inconsistent, upper 32b of %#010x updating too quickly\n",
+			      reg * 4);
+
+	/* Return only the upper bits as we cannot guarantee
+	 * the accuracy of the lower bits. We will add them in
+	 * when the counter slows down enough that we can get
+	 * a snapshot with both upper values being the same
+	 * between reads.
+	 */
+	return ((u64)upper << 32);
+}
+
+static void fbnic_hw_stat_rst64(struct fbnic_dev *fbd, u32 reg, s32 offset,
+				struct fbnic_stat_counter *stat)
+{
+	/* Record initial counter values and compute deltas from there to ensure
+	 * stats start at 0 after reboot/reset. This avoids exposing absolute
+	 * hardware counter values to userspace.
+	 */
+	stat->u.old_reg_value_64 = fbnic_stat_rd64(fbd, reg, offset);
+}
+
+static void fbnic_hw_stat_rd64(struct fbnic_dev *fbd, u32 reg, s32 offset,
+			       struct fbnic_stat_counter *stat)
+{
+	u64 new_reg_value;
+
+	new_reg_value = fbnic_stat_rd64(fbd, reg, offset);
+	stat->value += new_reg_value - stat->u.old_reg_value_64;
+	stat->u.old_reg_value_64 = new_reg_value;
+}
+
+static void fbnic_reset_tmi_stats(struct fbnic_dev *fbd,
+				  struct fbnic_tmi_stats *tmi)
+{
+	fbnic_hw_stat_rst32(fbd, FBNIC_TMI_DROP_PKTS, &tmi->drop.frames);
+	fbnic_hw_stat_rst64(fbd, FBNIC_TMI_DROP_BYTE_L, 1, &tmi->drop.bytes);
+
+	fbnic_hw_stat_rst32(fbd,
+			    FBNIC_TMI_ILLEGAL_PTP_REQS,
+			    &tmi->ptp_illegal_req);
+	fbnic_hw_stat_rst32(fbd, FBNIC_TMI_GOOD_PTP_TS, &tmi->ptp_good_ts);
+	fbnic_hw_stat_rst32(fbd, FBNIC_TMI_BAD_PTP_TS, &tmi->ptp_bad_ts);
+}
+
+static void fbnic_get_tmi_stats32(struct fbnic_dev *fbd,
+				  struct fbnic_tmi_stats *tmi)
+{
+	fbnic_hw_stat_rd32(fbd, FBNIC_TMI_DROP_PKTS, &tmi->drop.frames);
+
+	fbnic_hw_stat_rd32(fbd,
+			   FBNIC_TMI_ILLEGAL_PTP_REQS,
+			   &tmi->ptp_illegal_req);
+	fbnic_hw_stat_rd32(fbd, FBNIC_TMI_GOOD_PTP_TS, &tmi->ptp_good_ts);
+	fbnic_hw_stat_rd32(fbd, FBNIC_TMI_BAD_PTP_TS, &tmi->ptp_bad_ts);
+}
+
+static void fbnic_get_tmi_stats(struct fbnic_dev *fbd,
+				struct fbnic_tmi_stats *tmi)
+{
+	fbnic_hw_stat_rd64(fbd, FBNIC_TMI_DROP_BYTE_L, 1, &tmi->drop.bytes);
+}
+
+static void fbnic_reset_tti_stats(struct fbnic_dev *fbd,
+				  struct fbnic_tti_stats *tti)
+{
+	fbnic_hw_stat_rst32(fbd,
+			    FBNIC_TCE_TTI_CM_DROP_PKTS,
+			    &tti->cm_drop.frames);
+	fbnic_hw_stat_rst64(fbd,
+			    FBNIC_TCE_TTI_CM_DROP_BYTE_L,
+			    1,
+			    &tti->cm_drop.bytes);
+
+	fbnic_hw_stat_rst32(fbd,
+			    FBNIC_TCE_TTI_FRAME_DROP_PKTS,
+			    &tti->frame_drop.frames);
+	fbnic_hw_stat_rst64(fbd,
+			    FBNIC_TCE_TTI_FRAME_DROP_BYTE_L,
+			    1,
+			    &tti->frame_drop.bytes);
+
+	fbnic_hw_stat_rst32(fbd,
+			    FBNIC_TCE_TBI_DROP_PKTS,
+			    &tti->tbi_drop.frames);
+	fbnic_hw_stat_rst64(fbd,
+			    FBNIC_TCE_TBI_DROP_BYTE_L,
+			    1,
+			    &tti->tbi_drop.bytes);
+}
+
+static void fbnic_get_tti_stats32(struct fbnic_dev *fbd,
+				  struct fbnic_tti_stats *tti)
+{
+	fbnic_hw_stat_rd32(fbd,
+			   FBNIC_TCE_TTI_CM_DROP_PKTS,
+			   &tti->cm_drop.frames);
+
+	fbnic_hw_stat_rd32(fbd,
+			   FBNIC_TCE_TTI_FRAME_DROP_PKTS,
+			   &tti->frame_drop.frames);
+
+	fbnic_hw_stat_rd32(fbd,
+			   FBNIC_TCE_TBI_DROP_PKTS,
+			   &tti->tbi_drop.frames);
+}
+
+static void fbnic_get_tti_stats(struct fbnic_dev *fbd,
+				struct fbnic_tti_stats *tti)
+{
+	fbnic_hw_stat_rd64(fbd,
+			   FBNIC_TCE_TTI_CM_DROP_BYTE_L,
+			   1,
+			   &tti->cm_drop.bytes);
+
+	fbnic_hw_stat_rd64(fbd,
+			   FBNIC_TCE_TTI_FRAME_DROP_BYTE_L,
+			   1,
+			   &tti->frame_drop.bytes);
+
+	fbnic_hw_stat_rd64(fbd,
+			   FBNIC_TCE_TBI_DROP_BYTE_L,
+			   1,
+			   &tti->tbi_drop.bytes);
+}
+
+static void fbnic_reset_rpc_stats(struct fbnic_dev *fbd,
+				  struct fbnic_rpc_stats *rpc)
+{
+	fbnic_hw_stat_rst32(fbd,
+			    FBNIC_RPC_CNTR_UNKN_ETYPE,
+			    &rpc->unkn_etype);
+	fbnic_hw_stat_rst32(fbd,
+			    FBNIC_RPC_CNTR_UNKN_EXT_HDR,
+			    &rpc->unkn_ext_hdr);
+	fbnic_hw_stat_rst32(fbd, FBNIC_RPC_CNTR_IPV4_FRAG, &rpc->ipv4_frag);
+	fbnic_hw_stat_rst32(fbd, FBNIC_RPC_CNTR_IPV6_FRAG, &rpc->ipv6_frag);
+	fbnic_hw_stat_rst32(fbd, FBNIC_RPC_CNTR_IPV4_ESP, &rpc->ipv4_esp);
+	fbnic_hw_stat_rst32(fbd, FBNIC_RPC_CNTR_IPV6_ESP, &rpc->ipv6_esp);
+	fbnic_hw_stat_rst32(fbd, FBNIC_RPC_CNTR_TCP_OPT_ERR, &rpc->tcp_opt_err);
+	fbnic_hw_stat_rst32(fbd,
+			    FBNIC_RPC_CNTR_OUT_OF_HDR_ERR,
+			    &rpc->out_of_hdr_err);
+	fbnic_hw_stat_rst32(fbd,
+			    FBNIC_RPC_CNTR_OVR_SIZE_ERR,
+			    &rpc->ovr_size_err);
+}
+
+static void fbnic_get_rpc_stats32(struct fbnic_dev *fbd,
+				  struct fbnic_rpc_stats *rpc)
+{
+	fbnic_hw_stat_rd32(fbd,
+			   FBNIC_RPC_CNTR_UNKN_ETYPE,
+			   &rpc->unkn_etype);
+	fbnic_hw_stat_rd32(fbd,
+			   FBNIC_RPC_CNTR_UNKN_EXT_HDR,
+			   &rpc->unkn_ext_hdr);
+
+	fbnic_hw_stat_rd32(fbd, FBNIC_RPC_CNTR_IPV4_FRAG, &rpc->ipv4_frag);
+	fbnic_hw_stat_rd32(fbd, FBNIC_RPC_CNTR_IPV6_FRAG, &rpc->ipv6_frag);
+
+	fbnic_hw_stat_rd32(fbd, FBNIC_RPC_CNTR_IPV4_ESP, &rpc->ipv4_esp);
+	fbnic_hw_stat_rd32(fbd, FBNIC_RPC_CNTR_IPV6_ESP, &rpc->ipv6_esp);
+
+	fbnic_hw_stat_rd32(fbd, FBNIC_RPC_CNTR_TCP_OPT_ERR, &rpc->tcp_opt_err);
+	fbnic_hw_stat_rd32(fbd,
+			   FBNIC_RPC_CNTR_OUT_OF_HDR_ERR,
+			   &rpc->out_of_hdr_err);
+	fbnic_hw_stat_rd32(fbd,
+			   FBNIC_RPC_CNTR_OVR_SIZE_ERR,
+			   &rpc->ovr_size_err);
+}
+
+static void fbnic_reset_rxb_fifo_stats(struct fbnic_dev *fbd, int i,
+				       struct fbnic_rxb_fifo_stats *fifo)
+{
+	fbnic_hw_stat_rst32(fbd, FBNIC_RXB_DROP_FRMS_STS(i),
+			    &fifo->drop.frames);
+	fbnic_hw_stat_rst64(fbd, FBNIC_RXB_DROP_BYTES_STS_L(i), 1,
+			    &fifo->drop.bytes);
+
+	fbnic_hw_stat_rst32(fbd, FBNIC_RXB_TRUN_FRMS_STS(i),
+			    &fifo->trunc.frames);
+	fbnic_hw_stat_rst64(fbd, FBNIC_RXB_TRUN_BYTES_STS_L(i), 1,
+			    &fifo->trunc.bytes);
+
+	fbnic_hw_stat_rst32(fbd, FBNIC_RXB_TRANS_DROP_STS(i),
+			    &fifo->trans_drop);
+	fbnic_hw_stat_rst32(fbd, FBNIC_RXB_TRANS_ECN_STS(i),
+			    &fifo->trans_ecn);
+
+	fifo->level.u.old_reg_value_32 = 0;
+}
+
+static void fbnic_reset_rxb_enq_stats(struct fbnic_dev *fbd, int i,
+				      struct fbnic_rxb_enqueue_stats *enq)
+{
+	fbnic_hw_stat_rst32(fbd, FBNIC_RXB_DRBO_FRM_CNT_SRC(i),
+			    &enq->drbo.frames);
+	fbnic_hw_stat_rst64(fbd, FBNIC_RXB_DRBO_BYTE_CNT_SRC_L(i), 4,
+			    &enq->drbo.bytes);
+
+	fbnic_hw_stat_rst32(fbd, FBNIC_RXB_INTEGRITY_ERR(i),
+			    &enq->integrity_err);
+	fbnic_hw_stat_rst32(fbd, FBNIC_RXB_MAC_ERR(i),
+			    &enq->mac_err);
+	fbnic_hw_stat_rst32(fbd, FBNIC_RXB_PARSER_ERR(i),
+			    &enq->parser_err);
+	fbnic_hw_stat_rst32(fbd, FBNIC_RXB_FRM_ERR(i),
+			    &enq->frm_err);
+}
+
+static void fbnic_reset_rxb_deq_stats(struct fbnic_dev *fbd, int i,
+				      struct fbnic_rxb_dequeue_stats *deq)
+{
+	fbnic_hw_stat_rst32(fbd, FBNIC_RXB_INTF_FRM_CNT_DST(i),
+			    &deq->intf.frames);
+	fbnic_hw_stat_rst64(fbd, FBNIC_RXB_INTF_BYTE_CNT_DST_L(i), 4,
+			    &deq->intf.bytes);
+
+	fbnic_hw_stat_rst32(fbd, FBNIC_RXB_PBUF_FRM_CNT_DST(i),
+			    &deq->pbuf.frames);
+	fbnic_hw_stat_rst64(fbd, FBNIC_RXB_PBUF_BYTE_CNT_DST_L(i), 4,
+			    &deq->pbuf.bytes);
+}
+
+static void fbnic_reset_rxb_stats(struct fbnic_dev *fbd,
+				  struct fbnic_rxb_stats *rxb)
+{
+	int i;
+
+	for (i = 0; i < FBNIC_RXB_FIFO_INDICES; i++)
+		fbnic_reset_rxb_fifo_stats(fbd, i, &rxb->fifo[i]);
+
+	for (i = 0; i < FBNIC_RXB_INTF_INDICES; i++) {
+		fbnic_reset_rxb_enq_stats(fbd, i, &rxb->enq[i]);
+		fbnic_reset_rxb_deq_stats(fbd, i, &rxb->deq[i]);
+	}
+}
+
+static void fbnic_get_rxb_fifo_stats32(struct fbnic_dev *fbd, int i,
+				       struct fbnic_rxb_fifo_stats *fifo)
+{
+	fbnic_hw_stat_rd32(fbd, FBNIC_RXB_DROP_FRMS_STS(i),
+			   &fifo->drop.frames);
+	fbnic_hw_stat_rd32(fbd, FBNIC_RXB_TRUN_FRMS_STS(i),
+			   &fifo->trunc.frames);
+
+	fbnic_hw_stat_rd32(fbd, FBNIC_RXB_TRANS_DROP_STS(i),
+			   &fifo->trans_drop);
+	fbnic_hw_stat_rd32(fbd, FBNIC_RXB_TRANS_ECN_STS(i),
+			   &fifo->trans_ecn);
+
+	fifo->level.value = rd32(fbd, FBNIC_RXB_PBUF_FIFO_LEVEL(i));
+}
+
+static void fbnic_get_rxb_fifo_stats(struct fbnic_dev *fbd, int i,
+				     struct fbnic_rxb_fifo_stats *fifo)
+{
+	fbnic_hw_stat_rd64(fbd, FBNIC_RXB_DROP_BYTES_STS_L(i), 1,
+			   &fifo->drop.bytes);
+	fbnic_hw_stat_rd64(fbd, FBNIC_RXB_TRUN_BYTES_STS_L(i), 1,
+			   &fifo->trunc.bytes);
+
+	fbnic_get_rxb_fifo_stats32(fbd, i, fifo);
+}
+
+static void fbnic_get_rxb_enq_stats32(struct fbnic_dev *fbd, int i,
+				      struct fbnic_rxb_enqueue_stats *enq)
+{
+	fbnic_hw_stat_rd32(fbd, FBNIC_RXB_DRBO_FRM_CNT_SRC(i),
+			   &enq->drbo.frames);
+
+	fbnic_hw_stat_rd32(fbd, FBNIC_RXB_INTEGRITY_ERR(i),
+			   &enq->integrity_err);
+	fbnic_hw_stat_rd32(fbd, FBNIC_RXB_MAC_ERR(i),
+			   &enq->mac_err);
+	fbnic_hw_stat_rd32(fbd, FBNIC_RXB_PARSER_ERR(i),
+			   &enq->parser_err);
+	fbnic_hw_stat_rd32(fbd, FBNIC_RXB_FRM_ERR(i),
+			   &enq->frm_err);
+}
+
+static void fbnic_get_rxb_enq_stats(struct fbnic_dev *fbd, int i,
+				    struct fbnic_rxb_enqueue_stats *enq)
+{
+	fbnic_hw_stat_rd64(fbd, FBNIC_RXB_DRBO_BYTE_CNT_SRC_L(i), 4,
+			   &enq->drbo.bytes);
+
+	fbnic_get_rxb_enq_stats32(fbd, i, enq);
+}
+
+static void fbnic_get_rxb_deq_stats32(struct fbnic_dev *fbd, int i,
+				      struct fbnic_rxb_dequeue_stats *deq)
+{
+	fbnic_hw_stat_rd32(fbd, FBNIC_RXB_INTF_FRM_CNT_DST(i),
+			   &deq->intf.frames);
+	fbnic_hw_stat_rd32(fbd, FBNIC_RXB_PBUF_FRM_CNT_DST(i),
+			   &deq->pbuf.frames);
+}
+
+static void fbnic_get_rxb_deq_stats(struct fbnic_dev *fbd, int i,
+				    struct fbnic_rxb_dequeue_stats *deq)
+{
+	fbnic_hw_stat_rd64(fbd, FBNIC_RXB_INTF_BYTE_CNT_DST_L(i), 4,
+			   &deq->intf.bytes);
+	fbnic_hw_stat_rd64(fbd, FBNIC_RXB_PBUF_BYTE_CNT_DST_L(i), 4,
+			   &deq->pbuf.bytes);
+
+	fbnic_get_rxb_deq_stats32(fbd, i, deq);
+}
+
+static void fbnic_get_rxb_stats32(struct fbnic_dev *fbd,
+				  struct fbnic_rxb_stats *rxb)
+{
+	int i;
+
+	for (i = 0; i < FBNIC_RXB_FIFO_INDICES; i++)
+		fbnic_get_rxb_fifo_stats32(fbd, i, &rxb->fifo[i]);
+
+	for (i = 0; i < FBNIC_RXB_INTF_INDICES; i++) {
+		fbnic_get_rxb_enq_stats32(fbd, i, &rxb->enq[i]);
+		fbnic_get_rxb_deq_stats32(fbd, i, &rxb->deq[i]);
+	}
+}
+
+static void fbnic_get_rxb_stats(struct fbnic_dev *fbd,
+				struct fbnic_rxb_stats *rxb)
+{
+	int i;
+
+	for (i = 0; i < FBNIC_RXB_FIFO_INDICES; i++)
+		fbnic_get_rxb_fifo_stats(fbd, i, &rxb->fifo[i]);
+
+	for (i = 0; i < FBNIC_RXB_INTF_INDICES; i++) {
+		fbnic_get_rxb_enq_stats(fbd, i, &rxb->enq[i]);
+		fbnic_get_rxb_deq_stats(fbd, i, &rxb->deq[i]);
+	}
+}
+
+static void fbnic_reset_hw_rxq_stats(struct fbnic_dev *fbd,
+				     struct fbnic_hw_q_stats *hw_q)
+{
+	int i;
+
+	for (i = 0; i < fbd->max_num_queues; i++, hw_q++) {
+		u32 base = FBNIC_QUEUE(i);
+
+		fbnic_hw_stat_rst32(fbd,
+				    base + FBNIC_QUEUE_RDE_PKT_ERR_CNT,
+				    &hw_q->rde_pkt_err);
+		fbnic_hw_stat_rst32(fbd,
+				    base + FBNIC_QUEUE_RDE_CQ_DROP_CNT,
+				    &hw_q->rde_pkt_cq_drop);
+		fbnic_hw_stat_rst32(fbd,
+				    base + FBNIC_QUEUE_RDE_BDQ_DROP_CNT,
+				    &hw_q->rde_pkt_bdq_drop);
+	}
+}
+
+static void fbnic_get_hw_rxq_stats32(struct fbnic_dev *fbd,
+				     struct fbnic_hw_q_stats *hw_q)
+{
+	int i;
+
+	for (i = 0; i < fbd->max_num_queues; i++, hw_q++) {
+		u32 base = FBNIC_QUEUE(i);
+
+		fbnic_hw_stat_rd32(fbd,
+				   base + FBNIC_QUEUE_RDE_PKT_ERR_CNT,
+				   &hw_q->rde_pkt_err);
+		fbnic_hw_stat_rd32(fbd,
+				   base + FBNIC_QUEUE_RDE_CQ_DROP_CNT,
+				   &hw_q->rde_pkt_cq_drop);
+		fbnic_hw_stat_rd32(fbd,
+				   base + FBNIC_QUEUE_RDE_BDQ_DROP_CNT,
+				   &hw_q->rde_pkt_bdq_drop);
+	}
+}
+
+void fbnic_get_hw_q_stats(struct fbnic_dev *fbd,
+			  struct fbnic_hw_q_stats *hw_q)
+{
+	spin_lock(&fbd->hw_stats.lock);
+	fbnic_get_hw_rxq_stats32(fbd, hw_q);
+	spin_unlock(&fbd->hw_stats.lock);
+}
+
+static void fbnic_reset_pcie_stats_asic(struct fbnic_dev *fbd,
+					struct fbnic_pcie_stats *pcie)
+{
+	fbnic_hw_stat_rst64(fbd,
+			    FBNIC_PUL_USER_OB_RD_TLP_CNT_31_0,
+			    1,
+			    &pcie->ob_rd_tlp);
+	fbnic_hw_stat_rst64(fbd,
+			    FBNIC_PUL_USER_OB_RD_DWORD_CNT_31_0,
+			    1,
+			    &pcie->ob_rd_dword);
+	fbnic_hw_stat_rst64(fbd,
+			    FBNIC_PUL_USER_OB_CPL_TLP_CNT_31_0,
+			    1,
+			    &pcie->ob_cpl_tlp);
+	fbnic_hw_stat_rst64(fbd,
+			    FBNIC_PUL_USER_OB_CPL_DWORD_CNT_31_0,
+			    1,
+			    &pcie->ob_cpl_dword);
+	fbnic_hw_stat_rst64(fbd,
+			    FBNIC_PUL_USER_OB_WR_TLP_CNT_31_0,
+			    1,
+			    &pcie->ob_wr_tlp);
+	fbnic_hw_stat_rst64(fbd,
+			    FBNIC_PUL_USER_OB_WR_DWORD_CNT_31_0,
+			    1,
+			    &pcie->ob_wr_dword);
+
+	fbnic_hw_stat_rst64(fbd,
+			    FBNIC_PUL_USER_OB_RD_DBG_CNT_TAG_31_0,
+			    1,
+			    &pcie->ob_rd_no_tag);
+	fbnic_hw_stat_rst64(fbd,
+			    FBNIC_PUL_USER_OB_RD_DBG_CNT_CPL_CRED_31_0,
+			    1,
+			    &pcie->ob_rd_no_cpl_cred);
+	fbnic_hw_stat_rst64(fbd,
+			    FBNIC_PUL_USER_OB_RD_DBG_CNT_NP_CRED_31_0,
+			    1,
+			    &pcie->ob_rd_no_np_cred);
+}
+
+static void fbnic_get_pcie_stats_asic64(struct fbnic_dev *fbd,
+					struct fbnic_pcie_stats *pcie)
+{
+	fbnic_hw_stat_rd64(fbd,
+			   FBNIC_PUL_USER_OB_RD_TLP_CNT_31_0,
+			   1,
+			   &pcie->ob_rd_tlp);
+	fbnic_hw_stat_rd64(fbd,
+			   FBNIC_PUL_USER_OB_RD_DWORD_CNT_31_0,
+			   1,
+			   &pcie->ob_rd_dword);
+	fbnic_hw_stat_rd64(fbd,
+			   FBNIC_PUL_USER_OB_WR_TLP_CNT_31_0,
+			   1,
+			   &pcie->ob_wr_tlp);
+	fbnic_hw_stat_rd64(fbd,
+			   FBNIC_PUL_USER_OB_WR_DWORD_CNT_31_0,
+			   1,
+			   &pcie->ob_wr_dword);
+	fbnic_hw_stat_rd64(fbd,
+			   FBNIC_PUL_USER_OB_CPL_TLP_CNT_31_0,
+			   1,
+			   &pcie->ob_cpl_tlp);
+	fbnic_hw_stat_rd64(fbd,
+			   FBNIC_PUL_USER_OB_CPL_DWORD_CNT_31_0,
+			   1,
+			   &pcie->ob_cpl_dword);
+
+	fbnic_hw_stat_rd64(fbd,
+			   FBNIC_PUL_USER_OB_RD_DBG_CNT_TAG_31_0,
+			   1,
+			   &pcie->ob_rd_no_tag);
+	fbnic_hw_stat_rd64(fbd,
+			   FBNIC_PUL_USER_OB_RD_DBG_CNT_CPL_CRED_31_0,
+			   1,
+			   &pcie->ob_rd_no_cpl_cred);
+	fbnic_hw_stat_rd64(fbd,
+			   FBNIC_PUL_USER_OB_RD_DBG_CNT_NP_CRED_31_0,
+			   1,
+			   &pcie->ob_rd_no_np_cred);
+}
+
+static void fbnic_reset_phy_stats(struct fbnic_dev *fbd,
+				  struct fbnic_phy_stats *phy_stats)
+{
+	const struct fbnic_mac *mac = fbd->mac;
+
+	mac->get_fec_stats(fbd, true, &phy_stats->fec);
+	mac->get_pcs_stats(fbd, true, &phy_stats->pcs);
+}
+
+static void fbnic_get_phy_stats32(struct fbnic_dev *fbd,
+				  struct fbnic_phy_stats *phy_stats)
+{
+	const struct fbnic_mac *mac = fbd->mac;
+
+	mac->get_fec_stats(fbd, false, &phy_stats->fec);
+	mac->get_pcs_stats(fbd, false, &phy_stats->pcs);
+}
+
+static void fbnic_reset_hw_mac_stats(struct fbnic_dev *fbd,
+				     struct fbnic_mac_stats *mac_stats)
+{
+	const struct fbnic_mac *mac = fbd->mac;
+
+	mac->get_eth_mac_stats(fbd, true, &mac_stats->eth_mac);
+	mac->get_pause_stats(fbd, true, &mac_stats->pause);
+	mac->get_eth_ctrl_stats(fbd, true, &mac_stats->eth_ctrl);
+	mac->get_rmon_stats(fbd, true, &mac_stats->rmon);
+}
+
+void fbnic_reset_hw_stats(struct fbnic_dev *fbd)
+{
+	spin_lock(&fbd->hw_stats.lock);
+	fbnic_reset_phy_stats(fbd, &fbd->hw_stats.phy);
+	fbnic_reset_tmi_stats(fbd, &fbd->hw_stats.tmi);
+	fbnic_reset_tti_stats(fbd, &fbd->hw_stats.tti);
+	fbnic_reset_rpc_stats(fbd, &fbd->hw_stats.rpc);
+	fbnic_reset_rxb_stats(fbd, &fbd->hw_stats.rxb);
+	fbnic_reset_hw_rxq_stats(fbd, fbd->hw_stats.hw_q);
+	fbnic_reset_pcie_stats_asic(fbd, &fbd->hw_stats.pcie);
+	spin_unlock(&fbd->hw_stats.lock);
+
+	/* Once registered, the only other access to MAC stats is via the
+	 * ethtool API which is protected by the rtnl_lock. The call to
+	 * fbnic_reset_hw_stats() during PCI recovery is also protected
+	 * by the rtnl_lock hence, we don't need the spinlock to access
+	 * the MAC stats.
+	 */
+	if (fbd->netdev)
+		ASSERT_RTNL();
+	fbnic_reset_hw_mac_stats(fbd, &fbd->hw_stats.mac);
+}
+
+void fbnic_init_hw_stats(struct fbnic_dev *fbd)
+{
+	spin_lock_init(&fbd->hw_stats.lock);
+
+	fbnic_reset_hw_stats(fbd);
+}
+
+static void __fbnic_get_hw_stats32(struct fbnic_dev *fbd)
+{
+	fbnic_get_phy_stats32(fbd, &fbd->hw_stats.phy);
+	fbnic_get_tmi_stats32(fbd, &fbd->hw_stats.tmi);
+	fbnic_get_tti_stats32(fbd, &fbd->hw_stats.tti);
+	fbnic_get_rpc_stats32(fbd, &fbd->hw_stats.rpc);
+	fbnic_get_rxb_stats32(fbd, &fbd->hw_stats.rxb);
+	fbnic_get_hw_rxq_stats32(fbd, fbd->hw_stats.hw_q);
+}
+
+void fbnic_get_hw_stats32(struct fbnic_dev *fbd)
+{
+	spin_lock(&fbd->hw_stats.lock);
+	__fbnic_get_hw_stats32(fbd);
+	spin_unlock(&fbd->hw_stats.lock);
+}
+
+void fbnic_get_hw_stats(struct fbnic_dev *fbd)
+{
+	spin_lock(&fbd->hw_stats.lock);
+	__fbnic_get_hw_stats32(fbd);
+
+	fbnic_get_tmi_stats(fbd, &fbd->hw_stats.tmi);
+	fbnic_get_tti_stats(fbd, &fbd->hw_stats.tti);
+	fbnic_get_rxb_stats(fbd, &fbd->hw_stats.rxb);
+	fbnic_get_pcie_stats_asic64(fbd, &fbd->hw_stats.pcie);
+	spin_unlock(&fbd->hw_stats.lock);
+}

linux-7.2.3/drivers/net/ethernet/meta/fbnic/fbnic_hw_stats.h

@@ -0,0 +1,164 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) Meta Platforms, Inc. and affiliates. */
+
+#ifndef _FBNIC_HW_STATS_H_
+#define _FBNIC_HW_STATS_H_
+
+#include <linux/ethtool.h>
+#include <linux/spinlock.h>
+
+#include "fbnic_csr.h"
+
+struct fbnic_stat_counter {
+	u64 value;
+	union {
+		u32 old_reg_value_32;
+		u64 old_reg_value_64;
+	} u;
+	bool reported;
+};
+
+struct fbnic_hw_stat {
+	struct fbnic_stat_counter frames;
+	struct fbnic_stat_counter bytes;
+};
+
+struct fbnic_fec_stats {
+	struct fbnic_stat_counter corrected_blocks, uncorrectable_blocks;
+};
+
+struct fbnic_pcs_stats {
+	struct {
+		struct fbnic_stat_counter lanes[FBNIC_PCS_MAX_LANES];
+	} SymbolErrorDuringCarrier;
+};
+
+/* Note: not updated by fbnic_get_hw_stats() */
+struct fbnic_eth_ctrl_stats {
+	struct fbnic_stat_counter MACControlFramesTransmitted;
+	struct fbnic_stat_counter MACControlFramesReceived;
+};
+
+/* Note: not updated by fbnic_get_hw_stats() */
+struct fbnic_rmon_stats {
+	struct fbnic_stat_counter undersize_pkts;
+	struct fbnic_stat_counter oversize_pkts;
+	struct fbnic_stat_counter fragments;
+	struct fbnic_stat_counter jabbers;
+
+	struct fbnic_stat_counter hist[ETHTOOL_RMON_HIST_MAX];
+	struct fbnic_stat_counter hist_tx[ETHTOOL_RMON_HIST_MAX];
+};
+
+/* Note: not updated by fbnic_get_hw_stats() */
+struct fbnic_pause_stats {
+	struct fbnic_stat_counter tx_pause_frames;
+	struct fbnic_stat_counter rx_pause_frames;
+	struct fbnic_stat_counter tx_pause_storm_events;
+};
+
+struct fbnic_eth_mac_stats {
+	struct fbnic_stat_counter FramesTransmittedOK;
+	struct fbnic_stat_counter FramesReceivedOK;
+	struct fbnic_stat_counter FrameCheckSequenceErrors;
+	struct fbnic_stat_counter AlignmentErrors;
+	struct fbnic_stat_counter OctetsTransmittedOK;
+	struct fbnic_stat_counter FramesLostDueToIntMACXmitError;
+	struct fbnic_stat_counter OctetsReceivedOK;
+	struct fbnic_stat_counter FramesLostDueToIntMACRcvError;
+	struct fbnic_stat_counter MulticastFramesXmittedOK;
+	struct fbnic_stat_counter BroadcastFramesXmittedOK;
+	struct fbnic_stat_counter MulticastFramesReceivedOK;
+	struct fbnic_stat_counter BroadcastFramesReceivedOK;
+	struct fbnic_stat_counter FrameTooLongErrors;
+};
+
+struct fbnic_phy_stats {
+	struct fbnic_fec_stats fec;
+	struct fbnic_pcs_stats pcs;
+};
+
+struct fbnic_mac_stats {
+	struct fbnic_eth_mac_stats eth_mac;
+	struct fbnic_pause_stats pause;
+	struct fbnic_eth_ctrl_stats eth_ctrl;
+	struct fbnic_rmon_stats rmon;
+};
+
+struct fbnic_tmi_stats {
+	struct fbnic_hw_stat drop;
+	struct fbnic_stat_counter ptp_illegal_req, ptp_good_ts, ptp_bad_ts;
+};
+
+struct fbnic_tti_stats {
+	struct fbnic_hw_stat cm_drop, frame_drop, tbi_drop;
+};
+
+struct fbnic_rpc_stats {
+	struct fbnic_stat_counter unkn_etype, unkn_ext_hdr;
+	struct fbnic_stat_counter ipv4_frag, ipv6_frag, ipv4_esp, ipv6_esp;
+	struct fbnic_stat_counter tcp_opt_err, out_of_hdr_err, ovr_size_err;
+};
+
+struct fbnic_rxb_enqueue_stats {
+	struct fbnic_hw_stat drbo;
+	struct fbnic_stat_counter integrity_err, mac_err;
+	struct fbnic_stat_counter parser_err, frm_err;
+};
+
+struct fbnic_rxb_fifo_stats {
+	struct fbnic_hw_stat drop, trunc;
+	struct fbnic_stat_counter trans_drop, trans_ecn;
+	struct fbnic_stat_counter level;
+};
+
+struct fbnic_rxb_dequeue_stats {
+	struct fbnic_hw_stat intf, pbuf;
+};
+
+struct fbnic_rxb_stats {
+	struct fbnic_rxb_enqueue_stats enq[FBNIC_RXB_ENQUEUE_INDICES];
+	struct fbnic_rxb_fifo_stats fifo[FBNIC_RXB_FIFO_INDICES];
+	struct fbnic_rxb_dequeue_stats deq[FBNIC_RXB_DEQUEUE_INDICES];
+};
+
+struct fbnic_hw_q_stats {
+	struct fbnic_stat_counter rde_pkt_err;
+	struct fbnic_stat_counter rde_pkt_cq_drop;
+	struct fbnic_stat_counter rde_pkt_bdq_drop;
+};
+
+struct fbnic_pcie_stats {
+	struct fbnic_stat_counter ob_rd_tlp, ob_rd_dword;
+	struct fbnic_stat_counter ob_wr_tlp, ob_wr_dword;
+	struct fbnic_stat_counter ob_cpl_tlp, ob_cpl_dword;
+
+	struct fbnic_stat_counter ob_rd_no_tag;
+	struct fbnic_stat_counter ob_rd_no_cpl_cred;
+	struct fbnic_stat_counter ob_rd_no_np_cred;
+};
+
+struct fbnic_hw_stats {
+	struct fbnic_phy_stats phy;
+	struct fbnic_mac_stats mac;
+	struct fbnic_tmi_stats tmi;
+	struct fbnic_tti_stats tti;
+	struct fbnic_rpc_stats rpc;
+	struct fbnic_rxb_stats rxb;
+	struct fbnic_hw_q_stats hw_q[FBNIC_MAX_QUEUES];
+	struct fbnic_pcie_stats pcie;
+
+	/* Lock protecting the access to hw stats */
+	spinlock_t lock;
+};
+
+u64 fbnic_stat_rd64(struct fbnic_dev *fbd, u32 reg, u32 offset);
+
+void fbnic_reset_hw_stats(struct fbnic_dev *fbd);
+void fbnic_init_hw_stats(struct fbnic_dev *fbd);
+void fbnic_get_hw_q_stats(struct fbnic_dev *fbd,
+			  struct fbnic_hw_q_stats *hw_q);
+void fbnic_get_hw_stats32(struct fbnic_dev *fbd);
+void fbnic_get_hw_stats(struct fbnic_dev *fbd);
+
+#endif /* _FBNIC_HW_STATS_H_ */

linux-7.2.3/drivers/net/ethernet/meta/fbnic/fbnic_hwmon.c

@@ -0,0 +1,81 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) Meta Platforms, Inc. and affiliates. */
+
+#include <linux/hwmon.h>
+
+#include "fbnic.h"
+#include "fbnic_mac.h"
+
+static int fbnic_hwmon_sensor_id(enum hwmon_sensor_types type)
+{
+	if (type == hwmon_temp)
+		return FBNIC_SENSOR_TEMP;
+	if (type == hwmon_in)
+		return FBNIC_SENSOR_VOLTAGE;
+
+	return -EOPNOTSUPP;
+}
+
+static umode_t fbnic_hwmon_is_visible(const void *drvdata,
+				      enum hwmon_sensor_types type,
+				      u32 attr, int channel)
+{
+	if (type == hwmon_temp && attr == hwmon_temp_input)
+		return 0444;
+	if (type == hwmon_in && attr == hwmon_in_input)
+		return 0444;
+
+	return 0;
+}
+
+static int fbnic_hwmon_read(struct device *dev, enum hwmon_sensor_types type,
+			    u32 attr, int channel, long *val)
+{
+	struct fbnic_dev *fbd = dev_get_drvdata(dev);
+	const struct fbnic_mac *mac = fbd->mac;
+	int id;
+
+	id = fbnic_hwmon_sensor_id(type);
+	return id < 0 ? id : mac->get_sensor(fbd, id, val);
+}
+
+static const struct hwmon_ops fbnic_hwmon_ops = {
+	.is_visible = fbnic_hwmon_is_visible,
+	.read = fbnic_hwmon_read,
+};
+
+static const struct hwmon_channel_info *fbnic_hwmon_info[] = {
+	HWMON_CHANNEL_INFO(temp, HWMON_T_INPUT),
+	HWMON_CHANNEL_INFO(in, HWMON_I_INPUT),
+	NULL
+};
+
+static const struct hwmon_chip_info fbnic_chip_info = {
+	.ops = &fbnic_hwmon_ops,
+	.info = fbnic_hwmon_info,
+};
+
+void fbnic_hwmon_register(struct fbnic_dev *fbd)
+{
+	if (!IS_REACHABLE(CONFIG_HWMON))
+		return;
+
+	fbd->hwmon = hwmon_device_register_with_info(fbd->dev, "fbnic",
+						     fbd, &fbnic_chip_info,
+						     NULL);
+	if (IS_ERR(fbd->hwmon)) {
+		dev_notice(fbd->dev,
+			   "Failed to register hwmon device %pe\n",
+			   fbd->hwmon);
+		fbd->hwmon = NULL;
+	}
+}
+
+void fbnic_hwmon_unregister(struct fbnic_dev *fbd)
+{
+	if (!IS_REACHABLE(CONFIG_HWMON) || !fbd->hwmon)
+		return;
+
+	hwmon_device_unregister(fbd->hwmon);
+	fbd->hwmon = NULL;
+}

linux-7.2.3/drivers/net/ethernet/meta/fbnic/fbnic_irq.c

@@ -0,0 +1,469 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) Meta Platforms, Inc. and affiliates. */
+
+#include <linux/pci.h>
+#include <linux/types.h>
+
+#include "fbnic.h"
+#include "fbnic_netdev.h"
+#include "fbnic_txrx.h"
+
+static irqreturn_t fbnic_fw_msix_intr(int __always_unused irq, void *data)
+{
+	struct fbnic_dev *fbd = (struct fbnic_dev *)data;
+
+	fbnic_mbx_poll(fbd);
+
+	fbnic_wr32(fbd, FBNIC_INTR_MASK_CLEAR(0), 1u << FBNIC_FW_MSIX_ENTRY);
+
+	return IRQ_HANDLED;
+}
+
+static int __fbnic_fw_enable_mbx(struct fbnic_dev *fbd, int vector)
+{
+	int err;
+
+	/* Initialize mailbox and attempt to poll it into ready state */
+	fbnic_mbx_init(fbd);
+	err = fbnic_mbx_poll_tx_ready(fbd);
+	if (err) {
+		dev_warn(fbd->dev, "FW mailbox did not enter ready state\n");
+		return err;
+	}
+
+	/* Enable interrupt and unmask the vector */
+	enable_irq(vector);
+	fbnic_wr32(fbd, FBNIC_INTR_MASK_CLEAR(0), 1u << FBNIC_FW_MSIX_ENTRY);
+
+	return 0;
+}
+
+/**
+ * fbnic_fw_request_mbx - Configure and initialize Firmware Mailbox
+ * @fbd: Pointer to device to initialize
+ *
+ * This function will allocate the IRQ and then reinitialize the mailbox
+ * starting communication between the host and firmware.
+ *
+ * Return: non-zero on failure.
+ **/
+int fbnic_fw_request_mbx(struct fbnic_dev *fbd)
+{
+	struct pci_dev *pdev = to_pci_dev(fbd->dev);
+	int vector, err;
+
+	WARN_ON(fbd->fw_msix_vector);
+
+	vector = pci_irq_vector(pdev, FBNIC_FW_MSIX_ENTRY);
+	if (vector < 0)
+		return vector;
+
+	/* Request the IRQ for FW Mailbox vector. */
+	err = request_threaded_irq(vector, NULL, &fbnic_fw_msix_intr,
+				   IRQF_ONESHOT | IRQF_NO_AUTOEN,
+				   dev_name(fbd->dev), fbd);
+	if (err)
+		return err;
+
+	/* Initialize mailbox and attempt to poll it into ready state */
+	err = __fbnic_fw_enable_mbx(fbd, vector);
+	if (err)
+		free_irq(vector, fbd);
+
+	fbd->fw_msix_vector = vector;
+
+	return err;
+}
+
+/**
+ * fbnic_fw_disable_mbx - Temporarily place mailbox in standby state
+ * @fbd: Pointer to device
+ *
+ * Shutdown the mailbox by notifying the firmware to stop sending us logs, mask
+ * and synchronize the IRQ, and then clean up the rings.
+ **/
+static void fbnic_fw_disable_mbx(struct fbnic_dev *fbd)
+{
+	/* Disable interrupt and synchronize the IRQ */
+	disable_irq(fbd->fw_msix_vector);
+
+	/* Mask the vector */
+	fbnic_wr32(fbd, FBNIC_INTR_MASK_SET(0), 1u << FBNIC_FW_MSIX_ENTRY);
+
+	/* Make sure disabling logs message is sent, must be done here to
+	 * avoid risk of completing without a running interrupt.
+	 */
+	fbnic_mbx_flush_tx(fbd);
+	fbnic_mbx_clean(fbd);
+}
+
+/**
+ * fbnic_fw_free_mbx - Disable mailbox and place it in standby state
+ * @fbd: Pointer to device to disable
+ *
+ * This function will disable the mailbox interrupt, free any messages still
+ * in the mailbox and place it into a disabled state. The firmware is
+ * expected to see the update and assume that the host is in the reset state.
+ **/
+void fbnic_fw_free_mbx(struct fbnic_dev *fbd)
+{
+	/* Vector has already been freed */
+	if (!fbd->fw_msix_vector)
+		return;
+
+	fbnic_fw_disable_mbx(fbd);
+
+	/* Free the vector */
+	free_irq(fbd->fw_msix_vector, fbd);
+	fbd->fw_msix_vector = 0;
+}
+
+static irqreturn_t fbnic_mac_msix_intr(int __always_unused irq, void *data)
+{
+	struct fbnic_dev *fbd = data;
+	struct fbnic_net *fbn;
+
+	if (fbd->mac->get_link_event(fbd) == FBNIC_LINK_EVENT_NONE) {
+		fbnic_wr32(fbd, FBNIC_INTR_MASK_CLEAR(0),
+			   1u << FBNIC_PCS_MSIX_ENTRY);
+		return IRQ_HANDLED;
+	}
+
+	fbn = netdev_priv(fbd->netdev);
+
+	/* Record link down events */
+	if (!fbd->mac->get_link(fbd, fbn->aui, fbn->fec))
+		phylink_pcs_change(fbn->pcs, false);
+
+	return IRQ_HANDLED;
+}
+
+/**
+ * fbnic_mac_request_irq - Configure the MAC to enable it to advertise link
+ * @fbd: Pointer to device to initialize
+ *
+ * This function provides basic bringup for the MAC/PHY IRQ. For now the IRQ
+ * will remain disabled until we start the MAC/PCS/PHY logic via phylink.
+ *
+ * Return: non-zero on failure.
+ **/
+int fbnic_mac_request_irq(struct fbnic_dev *fbd)
+{
+	struct pci_dev *pdev = to_pci_dev(fbd->dev);
+	int vector, err;
+
+	WARN_ON(fbd->mac_msix_vector);
+
+	vector = pci_irq_vector(pdev, FBNIC_PCS_MSIX_ENTRY);
+	if (vector < 0)
+		return vector;
+
+	/* Request the IRQ for PCS link vector.
+	 * Map PCS cause to it, and unmask it
+	 */
+	err = request_irq(vector, &fbnic_mac_msix_intr, 0,
+			  fbd->netdev->name, fbd);
+	if (err)
+		return err;
+
+	/* Map and enable interrupt, unmask vector after link is configured */
+	fbnic_wr32(fbd, FBNIC_INTR_MSIX_CTRL(FBNIC_INTR_MSIX_CTRL_PCS_IDX),
+		   FBNIC_PCS_MSIX_ENTRY | FBNIC_INTR_MSIX_CTRL_ENABLE);
+
+	fbnic_wr32(fbd, FBNIC_INTR_MSIX_CTRL(FBNIC_INTR_MSIX_CTRL_RXB_IDX), 0);
+
+	fbd->mac_msix_vector = vector;
+
+	return 0;
+}
+
+/**
+ * fbnic_mac_free_irq - Teardown the MAC IRQ to prepare for stopping
+ * @fbd: Pointer to device that is stopping
+ *
+ * This function undoes the work done in fbnic_mac_request_irq and prepares
+ * the device to no longer receive traffic on the host interface.
+ **/
+void fbnic_mac_free_irq(struct fbnic_dev *fbd)
+{
+	/* Vector has already been freed */
+	if (!fbd->mac_msix_vector)
+		return;
+
+	/* Disable interrupt */
+	fbnic_wr32(fbd, FBNIC_INTR_MSIX_CTRL(FBNIC_INTR_MSIX_CTRL_PCS_IDX),
+		   FBNIC_PCS_MSIX_ENTRY);
+	fbnic_wrfl(fbd);
+
+	/* Synchronize IRQ to prevent race that would unmask vector */
+	synchronize_irq(fbd->mac_msix_vector);
+
+	/* Mask the vector */
+	fbnic_wr32(fbd, FBNIC_INTR_MASK_SET(0), 1u << FBNIC_PCS_MSIX_ENTRY);
+
+	/* Free the vector */
+	free_irq(fbd->mac_msix_vector, fbd);
+	fbd->mac_msix_vector = 0;
+}
+
+void fbnic_synchronize_irq(struct fbnic_dev *fbd, int nr)
+{
+	struct pci_dev *pdev = to_pci_dev(fbd->dev);
+	int irq = pci_irq_vector(pdev, nr);
+
+	if (irq < 0)
+		return;
+
+	synchronize_irq(irq);
+}
+
+int fbnic_request_irq(struct fbnic_dev *fbd, int nr, irq_handler_t handler,
+		      unsigned long flags, const char *name, void *data)
+{
+	struct pci_dev *pdev = to_pci_dev(fbd->dev);
+	int irq = pci_irq_vector(pdev, nr);
+
+	if (irq < 0)
+		return irq;
+
+	return request_irq(irq, handler, flags, name, data);
+}
+
+void fbnic_free_irq(struct fbnic_dev *fbd, int nr, void *data)
+{
+	struct pci_dev *pdev = to_pci_dev(fbd->dev);
+	int irq = pci_irq_vector(pdev, nr);
+
+	if (irq < 0)
+		return;
+
+	free_irq(irq, data);
+}
+
+struct fbnic_msix_test_data {
+	struct fbnic_dev *fbd;
+	unsigned long test_msix_status[BITS_TO_LONGS(FBNIC_MAX_MSIX_VECS)];
+	int irq_vector[FBNIC_MAX_MSIX_VECS];
+};
+
+static irqreturn_t fbnic_irq_test(int irq, void *data)
+{
+	struct fbnic_msix_test_data *test_data = data;
+	struct fbnic_dev *fbd = test_data->fbd;
+	int i;
+
+	for (i = fbd->num_irqs; i--;) {
+		if (test_data->irq_vector[i] == irq) {
+			set_bit(i, test_data->test_msix_status);
+			break;
+		}
+	}
+
+	return IRQ_HANDLED;
+}
+
+/**
+ * fbnic_msix_test - Verify behavior of NIC interrupts
+ * @fbd: device to test
+ *
+ * This function is meant to test the global interrupt registers and the
+ * PCIe IP MSI-X functionality. It essentially goes through and tests
+ * various combinations of the set, clear, and mask bits in order to
+ * verify the behavior is as we expect it to be from the driver.
+ *
+ * Return: See enum fbnic_msix_self_test_codes
+ **/
+enum fbnic_msix_self_test_codes fbnic_msix_test(struct fbnic_dev *fbd)
+{
+	enum fbnic_msix_self_test_codes result = FBNIC_TEST_MSIX_SUCCESS;
+	struct pci_dev *pdev = to_pci_dev(fbd->dev);
+	struct fbnic_msix_test_data *test_data;
+	u32 mask = 0;
+	int i;
+
+	/* Allocate bitmap and IRQ vector table */
+	test_data = kzalloc_obj(*test_data, GFP_KERNEL);
+
+	/* memory allocation failure */
+	if (!test_data)
+		return FBNIC_TEST_MSIX_NOMEM;
+
+	/* Initialize test data */
+	test_data->fbd = fbd;
+
+	for (i = FBNIC_NON_NAPI_VECTORS; i < fbd->num_irqs; i++) {
+		/* Add IRQ to vector table so it can be found */
+		test_data->irq_vector[i] = pci_irq_vector(pdev, i);
+
+		/* Enable the interrupt */
+		if (!fbnic_request_irq(fbd, i, fbnic_irq_test, 0,
+				       fbd->netdev->name, test_data))
+			continue;
+
+		while (i-- > FBNIC_NON_NAPI_VECTORS)
+			fbnic_free_irq(fbd, i, test_data);
+		kfree(test_data);
+
+		/* IRQ request failure */
+		return FBNIC_TEST_MSIX_IRQ_REQ_FAIL;
+	}
+
+	/* Test each bit individually */
+	for (i = FBNIC_NON_NAPI_VECTORS; i < fbd->num_irqs; i++) {
+		mask = 1U << (i % 32);
+
+		/* Start with mask set and interrupt cleared */
+		fbnic_wr32(fbd, FBNIC_INTR_MASK_SET(i / 32), mask);
+		fbnic_wrfl(fbd);
+		fbnic_wr32(fbd, FBNIC_INTR_CLEAR(i / 32), mask);
+		fbnic_wrfl(fbd);
+
+		/* masking failure to prevent interrupt */
+		result = FBNIC_TEST_MSIX_MASK;
+
+		fbnic_wr32(fbd, FBNIC_INTR_SET(i / 32), mask);
+		fbnic_wrfl(fbd);
+		usleep_range(10000, 11000);
+
+		if (test_bit(i, test_data->test_msix_status))
+			break;
+
+		/* unmasking failure w/ sw status set */
+		result = FBNIC_TEST_MSIX_UNMASK;
+
+		fbnic_wr32(fbd, FBNIC_INTR_MASK_CLEAR(i / 32), mask);
+		fbnic_wrfl(fbd);
+		usleep_range(10000, 11000);
+
+		if (!test_bit(i, test_data->test_msix_status))
+			break;
+
+		/* interrupt when clearing mask */
+		result = FBNIC_TEST_MSIX_IRQ_CLEAR;
+
+		clear_bit(i, test_data->test_msix_status);
+		fbnic_wr32(fbd, FBNIC_INTR_MASK_CLEAR(i / 32), mask);
+		fbnic_wrfl(fbd);
+		usleep_range(10000, 11000);
+
+		if (test_bit(i, test_data->test_msix_status))
+			break;
+
+		/* interrupt not triggering when not masked */
+		result = FBNIC_TEST_MSIX_NO_INTERRUPT;
+
+		fbnic_wr32(fbd, FBNIC_INTR_SET(i / 32), mask);
+		fbnic_wrfl(fbd);
+		usleep_range(10000, 11000);
+
+		if (!test_bit(i, test_data->test_msix_status))
+			break;
+
+		/* status not cleared, or mask not set */
+		result = FBNIC_TEST_MSIX_NO_CLEAR_OR_MASK;
+		if (mask & fbnic_rd32(fbd, FBNIC_INTR_STATUS(i / 32)))
+			break;
+		if (!(mask & fbnic_rd32(fbd, FBNIC_INTR_MASK(i / 32))))
+			break;
+
+		/* Result = 0 - Success */
+		result = FBNIC_TEST_MSIX_SUCCESS;
+
+		clear_bit(i, test_data->test_msix_status);
+	}
+
+	if (i < fbd->num_irqs) {
+		fbnic_wr32(fbd, FBNIC_INTR_MASK_SET(i / 32), mask);
+		fbnic_wrfl(fbd);
+		fbnic_wr32(fbd, FBNIC_INTR_CLEAR(i / 32), mask);
+		fbnic_wrfl(fbd);
+		clear_bit(i, test_data->test_msix_status);
+	}
+
+	for (i = FBNIC_NON_NAPI_VECTORS; i < fbd->num_irqs; i++) {
+		/* Test for bits set after testing */
+		if (test_bit(i, test_data->test_msix_status))
+			result = FBNIC_TEST_MSIX_BITS_SET_AFTER_TEST;
+
+		/* Free IRQ */
+		fbnic_free_irq(fbd, i, test_data);
+	}
+
+	kfree(test_data);
+
+	return result;
+}
+
+void fbnic_napi_name_irqs(struct fbnic_dev *fbd)
+{
+	unsigned int i;
+
+	for (i = 0; i < ARRAY_SIZE(fbd->napi_irq); i++)
+		snprintf(fbd->napi_irq[i].name,
+			 sizeof(fbd->napi_irq[i].name),
+			 "%s-TxRx-%u", fbd->netdev->name, i);
+}
+
+int fbnic_napi_request_irq(struct fbnic_dev *fbd,
+			   struct fbnic_napi_vector *nv)
+{
+	struct fbnic_net *fbn = netdev_priv(fbd->netdev);
+	int i = fbnic_napi_idx(nv);
+	int err;
+
+	if (!fbd->napi_irq[i].users) {
+		err = fbnic_request_irq(fbd, nv->v_idx,
+					fbnic_msix_clean_rings,	0,
+					fbd->napi_irq[i].name,
+					&fbn->napi[i]);
+		if (err)
+			return err;
+	}
+
+	fbd->napi_irq[i].users++;
+	return 0;
+}
+
+void fbnic_napi_free_irq(struct fbnic_dev *fbd,
+			 struct fbnic_napi_vector *nv)
+{
+	struct fbnic_net *fbn = netdev_priv(fbd->netdev);
+	int i = fbnic_napi_idx(nv);
+
+	if (--fbd->napi_irq[i].users)
+		return;
+
+	fbnic_free_irq(fbd, nv->v_idx, &fbn->napi[i]);
+}
+
+void fbnic_free_irqs(struct fbnic_dev *fbd)
+{
+	struct pci_dev *pdev = to_pci_dev(fbd->dev);
+
+	fbd->num_irqs = 0;
+
+	pci_free_irq_vectors(pdev);
+}
+
+int fbnic_alloc_irqs(struct fbnic_dev *fbd)
+{
+	unsigned int wanted_irqs = FBNIC_NON_NAPI_VECTORS;
+	struct pci_dev *pdev = to_pci_dev(fbd->dev);
+	int num_irqs;
+
+	wanted_irqs += min_t(unsigned int, num_online_cpus(), FBNIC_MAX_RXQS);
+	num_irqs = pci_alloc_irq_vectors(pdev, FBNIC_NON_NAPI_VECTORS + 1,
+					 wanted_irqs, PCI_IRQ_MSIX);
+	if (num_irqs < 0) {
+		dev_err(fbd->dev, "Failed to allocate MSI-X entries\n");
+		return num_irqs;
+	}
+
+	if (num_irqs < wanted_irqs)
+		dev_warn(fbd->dev, "Allocated %d IRQs, expected %d\n",
+			 num_irqs, wanted_irqs);
+
+	fbd->num_irqs = num_irqs;
+
+	return 0;
+}

linux-7.2.3/drivers/net/ethernet/meta/fbnic/fbnic_mac.h

@@ -0,0 +1,149 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) Meta Platforms, Inc. and affiliates. */
+
+#ifndef _FBNIC_MAC_H_
+#define _FBNIC_MAC_H_
+
+#include <linux/types.h>
+
+struct fbnic_dev;
+
+/* The RXB clock runs at 600 MHZ in the ASIC and the PAUSE_STORM_UNIT_WR
+ * is 10us granularity, so set the clock to 6000 (0x1770)
+ */
+#define FBNIC_RXB_PS_CLK_DIV		0x1770
+
+/* Convert milliseconds to pause storm timeout units (10us granularity) */
+#define FBNIC_MAC_RXB_PS_TO(ms)		((ms) * 100)
+
+/* Convert pause storm timeout units (10us granularity) to milliseconds */
+#define FBNIC_MAC_RXB_PS_TO_MS(ps)	((ps) / 100)
+
+/* Set the default timer to 500ms, which should be longer than any
+ * reasonable period of continuous pausing. The service task, which runs
+ * once per second, periodically resets the pause storm trigger.
+ *
+ * As a result, on a functioning system, if pause continues, we enforce
+ * a duty cycle determined by the configured pause storm timeout (50%
+ * default). A crashed system will not have the service task and therefore
+ * pause will remain disabled until reboot recovery.
+ */
+#define FBNIC_MAC_PS_TO_DEFAULT_MS	500
+#define FBNIC_MAC_PS_TO_MAX_MS	\
+	FBNIC_MAC_RXB_PS_TO_MS(FIELD_MAX(FBNIC_RXB_PAUSE_STORM_THLD_TIME))
+
+#define FBNIC_MAX_JUMBO_FRAME_SIZE	9742
+
+/* States loosely based on section 136.8.11.7.5 of IEEE 802.3-2022 Ethernet
+ * Standard.  These are needed to track the state of the PHY as it has a delay
+ * of several seconds from the time link comes up until it has completed
+ * training that we need to wait to report the link.
+ *
+ * Currently we treat training as a single block as this is managed by the
+ * firmware.
+ *
+ * We have FBNIC_PMD_SEND_DATA set to 0 as the expected default at driver load
+ * and we initialize the structure containing it to zero at allocation.
+ */
+enum {
+	FBNIC_PMD_SEND_DATA	= 0x0,
+	FBNIC_PMD_INITIALIZE	= 0x1,
+	FBNIC_PMD_TRAINING	= 0x2,
+	FBNIC_PMD_LINK_READY	= 0x3,
+};
+
+enum {
+	FBNIC_LINK_EVENT_NONE	= 0,
+	FBNIC_LINK_EVENT_UP	= 1,
+	FBNIC_LINK_EVENT_DOWN	= 2,
+};
+
+/* Treat the FEC bits as a bitmask laid out as follows:
+ * Bit 0: RS Enabled
+ * Bit 1: BASER(Firecode) Enabled
+ * Bit 2: Retrieve FEC from FW
+ */
+enum {
+	FBNIC_FEC_OFF		= 0,
+	FBNIC_FEC_RS		= 1,
+	FBNIC_FEC_BASER		= 2,
+};
+
+/* Treat the AUI modes as a modulation/lanes bitmask:
+ * Bit 0: Lane Count, 0 = R1, 1 = R2
+ * Bit 1: Modulation, 0 = NRZ, 1 = PAM4
+ * Bit 2: Unknown Modulation/Lane Configuration
+ */
+enum {
+	FBNIC_AUI_25GAUI	= 0,	/* 25.7812GBd	25.78125 * 1 */
+	FBNIC_AUI_LAUI2		= 1,	/* 51.5625GBd	25.78128 * 2 */
+	FBNIC_AUI_50GAUI1	= 2,	/* 53.125GBd	53.125   * 1 */
+	FBNIC_AUI_100GAUI2	= 3,	/* 106.25GBd	53.125   * 2 */
+	FBNIC_AUI_UNKNOWN	= 4,
+	__FBNIC_AUI_MAX__
+};
+
+#define FBNIC_AUI_MODE_R2	(FBNIC_AUI_LAUI2)
+#define FBNIC_AUI_MODE_PAM4	(FBNIC_AUI_50GAUI1)
+
+enum fbnic_sensor_id {
+	FBNIC_SENSOR_TEMP,		/* Temp in millidegrees Centigrade */
+	FBNIC_SENSOR_VOLTAGE,		/* Voltage in millivolts */
+};
+
+/* This structure defines the interface hooks for the MAC. The MAC hooks
+ * will be configured as a const struct provided with a set of function
+ * pointers.
+ *
+ * void (*init_regs)(struct fbnic_dev *fbd);
+ *	Initialize MAC registers to enable Tx/Rx paths and FIFOs.
+ *
+ * int (*get_link_event)(struct fbnic_dev *fbd)
+ *	Get the current link event status, reports true if link has
+ *	changed to either FBNIC_LINK_EVENT_DOWN or FBNIC_LINK_EVENT_UP
+ * bool (*get_link)(struct fbnic_dev *fbd, u8 aui, u8 fec);
+ *	Check link status
+ *
+ * void (*prepare)(struct fbnic_dev *fbd, u8 aui, u8 fec);
+ *	Prepare PHY for init by fetching settings, disabling interrupts,
+ *	and sending an updated PHY config to FW if needed.
+ *
+ * void (*link_down)(struct fbnic_dev *fbd);
+ *	Configure MAC for link down event
+ * void (*link_up)(struct fbnic_dev *fbd, bool tx_pause, bool rx_pause);
+ *	Configure MAC for link up event;
+ *
+ */
+struct fbnic_mac {
+	void (*init_regs)(struct fbnic_dev *fbd);
+
+	int (*get_link_event)(struct fbnic_dev *fbd);
+	bool (*get_link)(struct fbnic_dev *fbd, u8 aui, u8 fec);
+
+	void (*prepare)(struct fbnic_dev *fbd, u8 aui, u8 fec);
+
+	void (*get_fec_stats)(struct fbnic_dev *fbd, bool reset,
+			      struct fbnic_fec_stats *fec_stats);
+	void (*get_pcs_stats)(struct fbnic_dev *fbd, bool reset,
+			      struct fbnic_pcs_stats *pcs_stats);
+	void (*get_eth_mac_stats)(struct fbnic_dev *fbd, bool reset,
+				  struct fbnic_eth_mac_stats *mac_stats);
+	void (*get_pause_stats)(struct fbnic_dev *fbd, bool reset,
+				struct fbnic_pause_stats *pause_stats);
+	void (*get_eth_ctrl_stats)(struct fbnic_dev *fbd, bool reset,
+				   struct fbnic_eth_ctrl_stats *ctrl_stats);
+	void (*get_rmon_stats)(struct fbnic_dev *fbd, bool reset,
+			       struct fbnic_rmon_stats *rmon_stats);
+
+	void (*link_down)(struct fbnic_dev *fbd);
+	void (*link_up)(struct fbnic_dev *fbd, bool tx_pause, bool rx_pause);
+
+	int (*get_sensor)(struct fbnic_dev *fbd, int id, long *val);
+};
+
+int fbnic_mac_init(struct fbnic_dev *fbd);
+void fbnic_mac_get_fw_settings(struct fbnic_dev *fbd, u8 *aui, u8 *fec);
+int fbnic_mac_ps_protect_to_config(struct fbnic_dev *fbd, u16 timeout);
+void fbnic_mac_ps_protect_handler(struct fbnic_dev *fbd);
+bool fbnic_mac_check_tx_pause(struct fbnic_dev *fbd);
+#endif /* _FBNIC_MAC_H_ */

linux-7.2.3/drivers/net/ethernet/meta/fbnic/fbnic_mdio.c

@@ -0,0 +1,282 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) Meta Platforms, Inc. and affiliates. */
+
+#include <linux/mdio.h>
+#include <linux/pcs/pcs-xpcs.h>
+
+#include "fbnic.h"
+#include "fbnic_netdev.h"
+
+/* fbnic MDIO Interface Layout
+ *
+ *        +-------------------+
+ *        |        MAC        |
+ *        +-------------------+
+ *            |   |   |   |  <-- 25GMII, 50GMII, or CGMII
+ *        +-------------------+
+ *  MMD 3 |        PCS        |
+ *        +-------------------+
+ *        |        FEC        |
+ *        +-------------------+
+ *  MMD 8 |  Separated PMA    |
+ *        +-------------------+
+ *              |       |     <-- PMD Service Interface
+ *        +-------------------+
+ *  MMD 1 |        PMD        |
+ *        +-------------------+
+ */
+
+#define DW_VENDOR		BIT(15)
+#define FBNIC_PCS_VENDOR	BIT(9)
+#define FBNIC_PCS_ZERO_MASK	(DW_VENDOR - FBNIC_PCS_VENDOR)
+
+static int
+fbnic_mdio_ids(int id, int regnum)
+{
+	/* return correct IDs */
+	switch (regnum) {
+	case MDIO_DEVID1:
+		return id >> 16;
+	case MDIO_DEVID2:
+		return id & 0xffff;
+	case MDIO_DEVS1:
+		return MDIO_DEVS_SEP_PMA1 | MDIO_DEVS_PMAPMD | MDIO_DEVS_PCS;
+	case MDIO_DEVS2:
+		return 0;
+	case MDIO_STAT2:
+		return MDIO_STAT2_DEVPRST_VAL;
+	}
+
+	return 0;
+}
+
+static int
+fbnic_mdio_read_pmd(struct fbnic_dev *fbd, int addr, int regnum)
+{
+	u8 aui = FBNIC_AUI_UNKNOWN;
+	struct fbnic_net *fbn;
+	int ret = 0;
+
+	/* We don't need a second PMD, just one can handle both lanes */
+	if (addr)
+		return 0;
+
+	if (fbd->netdev) {
+		fbn = netdev_priv(fbd->netdev);
+		if (fbn->aui < FBNIC_AUI_UNKNOWN)
+			aui = fbn->aui;
+	}
+
+	switch (regnum) {
+	case MDIO_PMA_RXDET:
+		/* If training isn't complete default to 0 */
+		if (fbd->pmd_state != FBNIC_PMD_SEND_DATA)
+			break;
+		/* Report either 1 or 2 lanes detected depending on config */
+		ret = (MDIO_PMD_RXDET_GLOBAL | MDIO_PMD_RXDET_0) |
+		      ((aui & FBNIC_AUI_MODE_R2) *
+		       (MDIO_PMD_RXDET_1 / FBNIC_AUI_MODE_R2));
+		break;
+	default:
+		ret = fbnic_mdio_ids(MP_FBNIC_XPCS_PMA_100G_ID, regnum);
+		break;
+	}
+
+	dev_dbg(fbd->dev,
+		"SWMII PMD Rd: Addr: %d RegNum: %d Value: 0x%04x\n",
+		addr, regnum, ret);
+
+	return ret;
+}
+
+static int
+fbnic_mdio_read_pcs(struct fbnic_dev *fbd, int addr, int regnum)
+{
+	int ret, offset = 0, overrides = 0;
+
+	/* We will need access to both PCS instances to get config info */
+	if (addr >= 2)
+		return 0;
+
+	/* Report 0 for reserved registers */
+	if (regnum & FBNIC_PCS_ZERO_MASK)
+		return 0;
+
+	/* Intercept and return correct ID for PCS */
+	switch (regnum) {
+	case MDIO_DEVID1 ... MDIO_DEVID2:
+		ret = fbnic_mdio_ids(DW_XPCS_ID, regnum);
+		break;
+	case MDIO_DEVS1:
+		/* DW IP returns MDIO_DEVS_SEP_PMA1, MDIO_DEVS_PMAPMD,
+		 * and MDIO_DEVS_PCS as 0
+		 */
+		overrides = fbnic_mdio_ids(DW_XPCS_ID, regnum);
+		fallthrough;
+	default:
+		/* Swap vendor page bit for FBNIC PCS vendor page bit */
+		if (regnum & DW_VENDOR)
+			offset ^= DW_VENDOR | FBNIC_PCS_VENDOR;
+
+		ret = fbnic_rd32(fbd, FBNIC_PCS_PAGE(addr) + (regnum ^ offset));
+		ret |= overrides;
+		break;
+	}
+
+	dev_dbg(fbd->dev,
+		"SWMII PCS Rd: Addr: %d RegNum: %d Value: 0x%04x\n",
+		addr, regnum, ret);
+
+	return ret;
+}
+
+static int
+fbnic_mdio_read_pma(struct fbnic_dev *fbd, int addr, int regnum)
+{
+	int ret = 0;
+
+	/* We will need access to both PMA instances to get config info */
+	if (addr >= 2)
+		return 0;
+
+	switch (regnum) {
+	case MDIO_PMA_RSFEC_CTRL ... MDIO_PMA_RSFEC_LANE_MAP:
+		ret = fbnic_rd32(fbd, FBNIC_RSFEC_CONTROL(addr) +
+				 regnum - MDIO_PMA_RSFEC_CTRL);
+		break;
+	default:
+		ret = fbnic_mdio_ids(MP_FBNIC_XPCS_PMA_100G_ID, regnum);
+		break;
+	}
+
+	dev_dbg(fbd->dev,
+		"SWMII PMA Rd: Addr: %d RegNum: %d Value: 0x%04x\n",
+		addr, regnum, ret);
+
+	return ret;
+}
+
+static int
+fbnic_mdio_read_c45(struct mii_bus *bus, int addr, int devnum, int regnum)
+{
+	struct fbnic_dev *fbd = bus->priv;
+
+	if (devnum == MDIO_MMD_PMAPMD)
+		return fbnic_mdio_read_pmd(fbd, addr, regnum);
+
+	if (devnum == MDIO_MMD_PCS)
+		return fbnic_mdio_read_pcs(fbd, addr, regnum);
+
+	if (devnum == MDIO_MMD_SEP_PMA1)
+		return fbnic_mdio_read_pma(fbd, addr, regnum);
+
+	return 0;
+}
+
+static void
+fbnic_mdio_write_pmd(struct fbnic_dev *fbd, int addr, int regnum, u16 val)
+{
+	dev_dbg(fbd->dev,
+		"SWMII PMD Wr: Addr: %d RegNum: %d Value: 0x%04x\n",
+		addr, regnum, val);
+}
+
+static void
+fbnic_mdio_write_pcs(struct fbnic_dev *fbd, int addr, int regnum, u16 val)
+{
+	dev_dbg(fbd->dev,
+		"SWMII PCS Wr: Addr: %d RegNum: %d Value: 0x%04x\n",
+		addr, regnum, val);
+
+	/* Allow access to both halves of PCS for 50R2 config */
+	if (addr >= 2)
+		return;
+
+	/* Skip write for reserved registers */
+	if (regnum & FBNIC_PCS_ZERO_MASK)
+		return;
+
+	/* Swap vendor page bit for FBNIC PCS vendor page bit */
+	if (regnum & DW_VENDOR)
+		regnum ^= DW_VENDOR | FBNIC_PCS_VENDOR;
+
+	fbnic_wr32(fbd, FBNIC_PCS_PAGE(addr) + regnum, val);
+}
+
+static void
+fbnic_mdio_write_pma(struct fbnic_dev *fbd, int addr, int regnum, u16 val)
+{
+	dev_dbg(fbd->dev,
+		"SWMII PMA Wr: Addr: %d RegNum: %d Value: 0x%04x\n",
+		addr, regnum, val);
+
+	if (addr >= 2)
+		return;
+
+	switch (regnum) {
+	case MDIO_PMA_RSFEC_CTRL ... MDIO_PMA_RSFEC_LANE_MAP:
+		fbnic_wr32(fbd, FBNIC_RSFEC_CONTROL(addr) +
+				regnum - MDIO_PMA_RSFEC_CTRL, val);
+		break;
+	default:
+		break;
+	}
+}
+
+static int
+fbnic_mdio_write_c45(struct mii_bus *bus, int addr, int devnum,
+		     int regnum, u16 val)
+{
+	struct fbnic_dev *fbd = bus->priv;
+
+	if (devnum == MDIO_MMD_PMAPMD)
+		fbnic_mdio_write_pmd(fbd, addr, regnum, val);
+
+	if (devnum == MDIO_MMD_PCS)
+		fbnic_mdio_write_pcs(fbd, addr, regnum, val);
+
+	if (devnum == MDIO_MMD_SEP_PMA1)
+		fbnic_mdio_write_pma(fbd, addr, regnum, val);
+
+	return 0;
+}
+
+/**
+ * fbnic_mdiobus_create - Create an MDIO bus to allow interfacing w/ PHYs
+ * @fbd: Pointer to FBNIC device structure to populate bus on
+ *
+ * Initialize an MDIO bus and place a pointer to it on the fbd struct. This bus
+ * will be used to interface with the PMA/PMD and PCS.
+ *
+ * Return: 0 on success, negative on failure
+ **/
+int fbnic_mdiobus_create(struct fbnic_dev *fbd)
+{
+	struct mii_bus *bus;
+	int err;
+
+	bus = devm_mdiobus_alloc(fbd->dev);
+	if (!bus)
+		return -ENOMEM;
+
+	bus->name = "fbnic_mii_bus";
+	bus->read_c45 = &fbnic_mdio_read_c45;
+	bus->write_c45 = &fbnic_mdio_write_c45;
+
+	/* Disable PHY auto probing. We will add PCS manually */
+	bus->phy_mask = ~0;
+
+	bus->parent = fbd->dev;
+	bus->priv = fbd;
+	snprintf(bus->id, MII_BUS_ID_SIZE, "%s-mii", dev_name(fbd->dev));
+
+	err = devm_mdiobus_register(fbd->dev, bus);
+	if (err) {
+		dev_err(fbd->dev, "Failed to create MDIO bus: %d\n", err);
+		return err;
+	}
+
+	fbd->mdio_bus = bus;
+
+	return 0;
+}

linux-7.2.3/drivers/net/ethernet/meta/fbnic/fbnic_netdev.c

@@ -0,0 +1,891 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) Meta Platforms, Inc. and affiliates. */
+
+#include <linux/etherdevice.h>
+#include <linux/ipv6.h>
+#include <linux/types.h>
+#include <net/netdev_queues.h>
+
+#include "fbnic.h"
+#include "fbnic_netdev.h"
+#include "fbnic_txrx.h"
+
+int __fbnic_open(struct fbnic_net *fbn)
+{
+	struct fbnic_dev *fbd = fbn->fbd;
+	int err;
+
+	err = fbnic_alloc_napi_vectors(fbn);
+	if (err)
+		return err;
+
+	err = fbnic_alloc_resources(fbn);
+	if (err)
+		goto free_napi_vectors;
+
+	err = fbnic_set_netif_queues(fbn);
+	if (err)
+		goto free_resources;
+
+	/* Send ownership message and flush to verify FW has seen it */
+	err = fbnic_fw_xmit_ownership_msg(fbd, true);
+	if (err) {
+		dev_warn(fbd->dev,
+			 "Error %d sending host ownership message to the firmware\n",
+			 err);
+		goto err_reset_queues;
+	}
+
+	err = fbnic_time_start(fbn);
+	if (err)
+		goto release_ownership;
+
+	err = fbnic_fw_init_heartbeat(fbd, false);
+	if (err)
+		goto time_stop;
+
+	err = fbnic_mac_request_irq(fbd);
+	if (err)
+		goto time_stop;
+
+	/* Pull the BMC config and initialize the RPC */
+	fbnic_bmc_rpc_init(fbd);
+	fbnic_rss_reinit(fbd, fbn);
+
+	phylink_resume(fbn->phylink);
+
+	return 0;
+time_stop:
+	fbnic_time_stop(fbn);
+release_ownership:
+	fbnic_fw_xmit_ownership_msg(fbn->fbd, false);
+err_reset_queues:
+	fbnic_reset_netif_queues(fbn);
+free_resources:
+	fbnic_free_resources(fbn);
+free_napi_vectors:
+	fbnic_free_napi_vectors(fbn);
+	return err;
+}
+
+static int fbnic_open(struct net_device *netdev)
+{
+	struct fbnic_net *fbn = netdev_priv(netdev);
+	int err;
+
+	fbnic_napi_name_irqs(fbn->fbd);
+
+	err = __fbnic_open(fbn);
+	if (!err)
+		fbnic_up(fbn);
+
+	return err;
+}
+
+static int fbnic_stop(struct net_device *netdev)
+{
+	struct fbnic_net *fbn = netdev_priv(netdev);
+
+	fbnic_mac_free_irq(fbn->fbd);
+	phylink_suspend(fbn->phylink, fbnic_bmc_present(fbn->fbd));
+
+	fbnic_down(fbn);
+
+	fbnic_time_stop(fbn);
+	fbnic_fw_xmit_ownership_msg(fbn->fbd, false);
+
+	fbnic_reset_netif_queues(fbn);
+	fbnic_free_resources(fbn);
+	fbnic_free_napi_vectors(fbn);
+
+	return 0;
+}
+
+static int fbnic_uc_sync(struct net_device *netdev, const unsigned char *addr)
+{
+	struct fbnic_net *fbn = netdev_priv(netdev);
+	struct fbnic_mac_addr *avail_addr;
+
+	if (WARN_ON(!is_valid_ether_addr(addr)))
+		return -EADDRNOTAVAIL;
+
+	avail_addr = __fbnic_uc_sync(fbn->fbd, addr);
+	if (!avail_addr)
+		return -ENOSPC;
+
+	/* Add type flag indicating this address is in use by the host */
+	set_bit(FBNIC_MAC_ADDR_T_UNICAST, avail_addr->act_tcam);
+
+	return 0;
+}
+
+static int fbnic_uc_unsync(struct net_device *netdev, const unsigned char *addr)
+{
+	struct fbnic_net *fbn = netdev_priv(netdev);
+	struct fbnic_dev *fbd = fbn->fbd;
+	int i, ret;
+
+	/* Scan from middle of list to bottom, filling bottom up.
+	 * Skip the first entry which is reserved for dev_addr and
+	 * leave the last entry to use for promiscuous filtering.
+	 */
+	for (i = fbd->mac_addr_boundary, ret = -ENOENT;
+	     i < FBNIC_RPC_TCAM_MACDA_HOST_ADDR_IDX && ret; i++) {
+		struct fbnic_mac_addr *mac_addr = &fbd->mac_addr[i];
+
+		if (!ether_addr_equal(mac_addr->value.addr8, addr))
+			continue;
+
+		ret = __fbnic_uc_unsync(mac_addr);
+	}
+
+	return ret;
+}
+
+static int fbnic_mc_sync(struct net_device *netdev, const unsigned char *addr)
+{
+	struct fbnic_net *fbn = netdev_priv(netdev);
+	struct fbnic_mac_addr *avail_addr;
+
+	if (WARN_ON(!is_multicast_ether_addr(addr)))
+		return -EADDRNOTAVAIL;
+
+	avail_addr = __fbnic_mc_sync(fbn->fbd, addr);
+	if (!avail_addr)
+		return -ENOSPC;
+
+	/* Add type flag indicating this address is in use by the host */
+	set_bit(FBNIC_MAC_ADDR_T_MULTICAST, avail_addr->act_tcam);
+
+	return 0;
+}
+
+static int fbnic_mc_unsync(struct net_device *netdev, const unsigned char *addr)
+{
+	struct fbnic_net *fbn = netdev_priv(netdev);
+	struct fbnic_dev *fbd = fbn->fbd;
+	int i, ret;
+
+	/* Scan from middle of list to top, filling top down.
+	 * Skip over the address reserved for the BMC MAC and
+	 * exclude index 0 as that belongs to the broadcast address
+	 */
+	for (i = fbd->mac_addr_boundary, ret = -ENOENT;
+	     --i > FBNIC_RPC_TCAM_MACDA_BROADCAST_IDX && ret;) {
+		struct fbnic_mac_addr *mac_addr = &fbd->mac_addr[i];
+
+		if (!ether_addr_equal(mac_addr->value.addr8, addr))
+			continue;
+
+		ret = __fbnic_mc_unsync(mac_addr);
+	}
+
+	return ret;
+}
+
+void __fbnic_set_rx_mode(struct fbnic_dev *fbd,
+			 struct netdev_hw_addr_list *uc,
+			 struct netdev_hw_addr_list *mc)
+{
+	bool uc_promisc = false, mc_promisc = false;
+	struct net_device *netdev = fbd->netdev;
+	struct fbnic_mac_addr *mac_addr;
+	int err;
+
+	/* Populate host address from dev_addr */
+	mac_addr = &fbd->mac_addr[FBNIC_RPC_TCAM_MACDA_HOST_ADDR_IDX];
+	if (!ether_addr_equal(mac_addr->value.addr8, netdev->dev_addr) ||
+	    mac_addr->state != FBNIC_TCAM_S_VALID) {
+		ether_addr_copy(mac_addr->value.addr8, netdev->dev_addr);
+		mac_addr->state = FBNIC_TCAM_S_UPDATE;
+		set_bit(FBNIC_MAC_ADDR_T_UNICAST, mac_addr->act_tcam);
+	}
+
+	/* Populate broadcast address if broadcast is enabled */
+	mac_addr = &fbd->mac_addr[FBNIC_RPC_TCAM_MACDA_BROADCAST_IDX];
+	if (netdev->flags & IFF_BROADCAST) {
+		if (!is_broadcast_ether_addr(mac_addr->value.addr8) ||
+		    mac_addr->state != FBNIC_TCAM_S_VALID) {
+			eth_broadcast_addr(mac_addr->value.addr8);
+			mac_addr->state = FBNIC_TCAM_S_ADD;
+		}
+		set_bit(FBNIC_MAC_ADDR_T_BROADCAST, mac_addr->act_tcam);
+	} else if (mac_addr->state == FBNIC_TCAM_S_VALID) {
+		__fbnic_xc_unsync(mac_addr, FBNIC_MAC_ADDR_T_BROADCAST);
+	}
+
+	/* Synchronize unicast and multicast address lists */
+	err = __hw_addr_sync_dev(uc, netdev, fbnic_uc_sync, fbnic_uc_unsync);
+	if (err == -ENOSPC)
+		uc_promisc = true;
+	err = __hw_addr_sync_dev(mc, netdev, fbnic_mc_sync, fbnic_mc_unsync);
+	if (err == -ENOSPC)
+		mc_promisc = true;
+
+	uc_promisc |= !!(netdev->flags & IFF_PROMISC);
+	mc_promisc |= !!(netdev->flags & IFF_ALLMULTI) || uc_promisc;
+
+	/* Update the promiscuous rules */
+	fbnic_promisc_sync(fbd, uc_promisc, mc_promisc);
+
+	/* Add rules for BMC all multicast if it is enabled */
+	fbnic_bmc_rpc_all_multi_config(fbd, mc_promisc);
+
+	/* Sift out any unshared BMC rules and place them in BMC only section */
+	fbnic_sift_macda(fbd);
+
+	/* Write updates to hardware */
+	fbnic_write_rules(fbd);
+	fbnic_write_macda(fbd);
+	fbnic_write_tce_tcam(fbd);
+}
+
+static int fbnic_set_rx_mode(struct net_device *netdev,
+			     struct netdev_hw_addr_list *uc,
+			     struct netdev_hw_addr_list *mc)
+{
+	struct fbnic_net *fbn = netdev_priv(netdev);
+	struct fbnic_dev *fbd = fbn->fbd;
+
+	/* No need to update the hardware if we are not running */
+	if (netif_running(netdev))
+		__fbnic_set_rx_mode(fbd, uc, mc);
+
+	return 0;
+}
+
+static int fbnic_set_mac(struct net_device *netdev, void *p)
+{
+	struct fbnic_net *fbn = netdev_priv(netdev);
+	struct sockaddr *addr = p;
+
+	if (!is_valid_ether_addr(addr->sa_data))
+		return -EADDRNOTAVAIL;
+
+	eth_hw_addr_set(netdev, addr->sa_data);
+
+	if (netif_running(netdev)) {
+		netif_addr_lock_bh(netdev);
+		__fbnic_set_rx_mode(fbn->fbd, &netdev->uc, &netdev->mc);
+		netif_addr_unlock_bh(netdev);
+	}
+
+	return 0;
+}
+
+static int fbnic_change_mtu(struct net_device *dev, int new_mtu)
+{
+	struct fbnic_net *fbn = netdev_priv(dev);
+
+	if (fbnic_check_split_frames(fbn->xdp_prog, new_mtu, fbn->hds_thresh)) {
+		dev_err(&dev->dev,
+			"MTU %d is larger than HDS threshold %d in XDP mode\n",
+			new_mtu, fbn->hds_thresh);
+
+		return -EINVAL;
+	}
+
+	WRITE_ONCE(dev->mtu, new_mtu);
+
+	return 0;
+}
+
+void fbnic_clear_rx_mode(struct fbnic_dev *fbd)
+{
+	struct net_device *netdev = fbd->netdev;
+	int idx;
+
+	for (idx = ARRAY_SIZE(fbd->mac_addr); idx--;) {
+		struct fbnic_mac_addr *mac_addr = &fbd->mac_addr[idx];
+
+		if (mac_addr->state != FBNIC_TCAM_S_VALID)
+			continue;
+
+		bitmap_clear(mac_addr->act_tcam,
+			     FBNIC_MAC_ADDR_T_HOST_START,
+			     FBNIC_MAC_ADDR_T_HOST_LEN);
+
+		if (bitmap_empty(mac_addr->act_tcam,
+				 FBNIC_RPC_TCAM_ACT_NUM_ENTRIES))
+			mac_addr->state = FBNIC_TCAM_S_DELETE;
+	}
+
+	/* Write updates to hardware */
+	fbnic_write_macda(fbd);
+
+	netif_addr_lock_bh(netdev);
+	__dev_uc_unsync(netdev, NULL);
+	__dev_mc_unsync(netdev, NULL);
+	netif_addr_unlock_bh(netdev);
+}
+
+static int fbnic_hwtstamp_get(struct net_device *netdev,
+			      struct kernel_hwtstamp_config *config)
+{
+	struct fbnic_net *fbn = netdev_priv(netdev);
+
+	*config = fbn->hwtstamp_config;
+
+	return 0;
+}
+
+static int fbnic_hwtstamp_set(struct net_device *netdev,
+			      struct kernel_hwtstamp_config *config,
+			      struct netlink_ext_ack *extack)
+{
+	struct fbnic_net *fbn = netdev_priv(netdev);
+	int old_rx_filter;
+
+	if (config->source != HWTSTAMP_SOURCE_NETDEV)
+		return -EOPNOTSUPP;
+
+	if (!kernel_hwtstamp_config_changed(config, &fbn->hwtstamp_config))
+		return 0;
+
+	/* Upscale the filters */
+	switch (config->rx_filter) {
+	case HWTSTAMP_FILTER_NONE:
+	case HWTSTAMP_FILTER_ALL:
+	case HWTSTAMP_FILTER_PTP_V1_L4_EVENT:
+	case HWTSTAMP_FILTER_PTP_V2_L4_EVENT:
+	case HWTSTAMP_FILTER_PTP_V2_L2_EVENT:
+	case HWTSTAMP_FILTER_PTP_V2_EVENT:
+		break;
+	case HWTSTAMP_FILTER_NTP_ALL:
+		config->rx_filter = HWTSTAMP_FILTER_ALL;
+		break;
+	case HWTSTAMP_FILTER_PTP_V1_L4_SYNC:
+	case HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ:
+		config->rx_filter = HWTSTAMP_FILTER_PTP_V1_L4_EVENT;
+		break;
+	case HWTSTAMP_FILTER_PTP_V2_L4_SYNC:
+	case HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ:
+		config->rx_filter = HWTSTAMP_FILTER_PTP_V2_L4_EVENT;
+		break;
+	case HWTSTAMP_FILTER_PTP_V2_L2_SYNC:
+	case HWTSTAMP_FILTER_PTP_V2_L2_DELAY_REQ:
+		config->rx_filter = HWTSTAMP_FILTER_PTP_V2_L2_EVENT;
+		break;
+	case HWTSTAMP_FILTER_PTP_V2_SYNC:
+	case HWTSTAMP_FILTER_PTP_V2_DELAY_REQ:
+		config->rx_filter = HWTSTAMP_FILTER_PTP_V2_EVENT;
+		break;
+	default:
+		return -ERANGE;
+	}
+
+	/* Configure */
+	old_rx_filter = fbn->hwtstamp_config.rx_filter;
+	memcpy(&fbn->hwtstamp_config, config, sizeof(*config));
+
+	if (old_rx_filter != config->rx_filter && netif_running(fbn->netdev)) {
+		fbnic_rss_reinit(fbn->fbd, fbn);
+		fbnic_write_rules(fbn->fbd);
+	}
+
+	/* Save / report back filter configuration
+	 * Note that our filter configuration is inexact. Instead of
+	 * filtering for a specific UDP port or L2 Ethertype we are
+	 * filtering in all UDP or all non-IP packets for timestamping. So
+	 * if anything other than FILTER_ALL is requested we report
+	 * FILTER_SOME indicating that we will be timestamping a few
+	 * additional packets.
+	 */
+	if (config->rx_filter > HWTSTAMP_FILTER_ALL)
+		config->rx_filter = HWTSTAMP_FILTER_SOME;
+
+	return 0;
+}
+
+static void fbnic_get_stats64(struct net_device *dev,
+			      struct rtnl_link_stats64 *stats64)
+{
+	u64 rx_bytes, rx_packets, rx_dropped = 0, rx_errors = 0;
+	u64 rx_over = 0, rx_missed = 0, rx_length = 0;
+	u64 tx_bytes, tx_packets, tx_dropped = 0;
+	struct fbnic_net *fbn = netdev_priv(dev);
+	struct fbnic_dev *fbd = fbn->fbd;
+	struct fbnic_queue_stats *stats;
+
+	unsigned int start, i;
+
+	fbnic_get_hw_stats(fbd);
+
+	stats = &fbn->tx_stats;
+
+	tx_bytes = stats->bytes;
+	tx_packets = stats->packets;
+	tx_dropped = stats->dropped;
+
+	/* Record drops from Tx HW Datapath */
+	spin_lock(&fbd->hw_stats.lock);
+	tx_dropped += fbd->hw_stats.tmi.drop.frames.value +
+		      fbd->hw_stats.tti.cm_drop.frames.value +
+		      fbd->hw_stats.tti.frame_drop.frames.value +
+		      fbd->hw_stats.tti.tbi_drop.frames.value;
+	spin_unlock(&fbd->hw_stats.lock);
+
+	stats64->tx_bytes = tx_bytes;
+	stats64->tx_packets = tx_packets;
+	stats64->tx_dropped = tx_dropped;
+
+	for (i = 0; i < fbn->num_tx_queues; i++) {
+		struct fbnic_ring *txr = fbn->tx[i];
+
+		if (!txr)
+			continue;
+
+		stats = &txr->stats;
+		do {
+			start = u64_stats_fetch_begin(&stats->syncp);
+			tx_bytes = stats->bytes;
+			tx_packets = stats->packets;
+			tx_dropped = stats->dropped;
+		} while (u64_stats_fetch_retry(&stats->syncp, start));
+
+		stats64->tx_bytes += tx_bytes;
+		stats64->tx_packets += tx_packets;
+		stats64->tx_dropped += tx_dropped;
+	}
+
+	stats = &fbn->rx_stats;
+
+	rx_bytes = stats->bytes;
+	rx_packets = stats->packets;
+	rx_dropped = stats->dropped;
+
+	spin_lock(&fbd->hw_stats.lock);
+	/* Record drops for the host FIFOs.
+	 * 4: network to Host,	6: BMC to Host
+	 * Exclude the BMC and MC FIFOs as those stats may contain drops
+	 * due to unrelated items such as TCAM misses. They are still
+	 * accessible through the ethtool stats.
+	 */
+	i = FBNIC_RXB_FIFO_HOST;
+	rx_missed += fbd->hw_stats.rxb.fifo[i].drop.frames.value;
+	i = FBNIC_RXB_FIFO_BMC_TO_HOST;
+	rx_missed += fbd->hw_stats.rxb.fifo[i].drop.frames.value;
+
+	for (i = 0; i < fbd->max_num_queues; i++) {
+		/* Report packets dropped due to CQ/BDQ being full/empty */
+		rx_over += fbd->hw_stats.hw_q[i].rde_pkt_cq_drop.value;
+		rx_over += fbd->hw_stats.hw_q[i].rde_pkt_bdq_drop.value;
+
+		/* Report packets with errors */
+		rx_errors += fbd->hw_stats.hw_q[i].rde_pkt_err.value;
+	}
+	spin_unlock(&fbd->hw_stats.lock);
+
+	stats64->rx_bytes = rx_bytes;
+	stats64->rx_packets = rx_packets;
+	stats64->rx_dropped = rx_dropped;
+	stats64->rx_over_errors = rx_over;
+	stats64->rx_errors = rx_errors;
+	stats64->rx_missed_errors = rx_missed;
+
+	for (i = 0; i < fbn->num_rx_queues; i++) {
+		struct fbnic_ring *xdpr = fbn->tx[FBNIC_MAX_TXQS + i];
+		struct fbnic_ring *rxr = fbn->rx[i];
+
+		if (!rxr)
+			continue;
+
+		stats = &rxr->stats;
+		do {
+			start = u64_stats_fetch_begin(&stats->syncp);
+			rx_bytes = stats->bytes;
+			rx_packets = stats->packets;
+			rx_dropped = stats->dropped;
+			rx_length = stats->rx.length_errors;
+		} while (u64_stats_fetch_retry(&stats->syncp, start));
+
+		stats64->rx_bytes += rx_bytes;
+		stats64->rx_packets += rx_packets;
+		stats64->rx_dropped += rx_dropped;
+		stats64->rx_errors += rx_length;
+		stats64->rx_length_errors += rx_length;
+
+		if (!xdpr)
+			continue;
+
+		stats = &xdpr->stats;
+		do {
+			start = u64_stats_fetch_begin(&stats->syncp);
+			tx_bytes = stats->bytes;
+			tx_packets = stats->packets;
+			tx_dropped = stats->dropped;
+		} while (u64_stats_fetch_retry(&stats->syncp, start));
+
+		stats64->tx_bytes += tx_bytes;
+		stats64->tx_packets += tx_packets;
+		stats64->tx_dropped += tx_dropped;
+	}
+}
+
+bool fbnic_check_split_frames(struct bpf_prog *prog, unsigned int mtu,
+			      u32 hds_thresh)
+{
+	if (!prog)
+		return false;
+
+	if (prog->aux->xdp_has_frags)
+		return false;
+
+	return mtu + ETH_HLEN > hds_thresh;
+}
+
+static int fbnic_bpf(struct net_device *netdev, struct netdev_bpf *bpf)
+{
+	struct bpf_prog *prog = bpf->prog, *prev_prog;
+	struct fbnic_net *fbn = netdev_priv(netdev);
+
+	if (bpf->command != XDP_SETUP_PROG)
+		return -EINVAL;
+
+	if (fbnic_check_split_frames(prog, netdev->mtu,
+				     fbn->hds_thresh)) {
+		NL_SET_ERR_MSG_MOD(bpf->extack,
+				   "MTU too high, or HDS threshold is too low for single buffer XDP");
+		return -EOPNOTSUPP;
+	}
+
+	prev_prog = xchg(&fbn->xdp_prog, prog);
+	if (prev_prog)
+		bpf_prog_put(prev_prog);
+
+	return 0;
+}
+
+static const struct net_device_ops fbnic_netdev_ops = {
+	.ndo_open		= fbnic_open,
+	.ndo_stop		= fbnic_stop,
+	.ndo_validate_addr	= eth_validate_addr,
+	.ndo_start_xmit		= fbnic_xmit_frame,
+	.ndo_features_check	= fbnic_features_check,
+	.ndo_set_mac_address	= fbnic_set_mac,
+	.ndo_change_mtu		= fbnic_change_mtu,
+	.ndo_set_rx_mode_async	= fbnic_set_rx_mode,
+	.ndo_get_stats64	= fbnic_get_stats64,
+	.ndo_bpf		= fbnic_bpf,
+	.ndo_hwtstamp_get	= fbnic_hwtstamp_get,
+	.ndo_hwtstamp_set	= fbnic_hwtstamp_set,
+};
+
+static void fbnic_get_queue_stats_rx(struct net_device *dev, int idx,
+				     struct netdev_queue_stats_rx *rx)
+{
+	u64 bytes, packets, alloc_fail, alloc_fail_bdq;
+	struct fbnic_net *fbn = netdev_priv(dev);
+	struct fbnic_ring *rxr = fbn->rx[idx];
+	struct fbnic_dev *fbd = fbn->fbd;
+	struct fbnic_queue_stats *stats;
+	u64 csum_complete, csum_none;
+	struct fbnic_q_triad *qt;
+	unsigned int start;
+
+	if (!rxr)
+		return;
+
+	/* fbn->rx points to completion queues */
+	qt = container_of(rxr, struct fbnic_q_triad, cmpl);
+
+	stats = &rxr->stats;
+	do {
+		start = u64_stats_fetch_begin(&stats->syncp);
+		bytes = stats->bytes;
+		packets = stats->packets;
+		alloc_fail = stats->rx.alloc_failed;
+		csum_complete = stats->rx.csum_complete;
+		csum_none = stats->rx.csum_none;
+	} while (u64_stats_fetch_retry(&stats->syncp, start));
+
+	stats = &qt->sub0.stats;
+	do {
+		start = u64_stats_fetch_begin(&stats->syncp);
+		alloc_fail_bdq = stats->bdq.alloc_failed;
+	} while (u64_stats_fetch_retry(&stats->syncp, start));
+	alloc_fail += alloc_fail_bdq;
+
+	stats = &qt->sub1.stats;
+	do {
+		start = u64_stats_fetch_begin(&stats->syncp);
+		alloc_fail_bdq = stats->bdq.alloc_failed;
+	} while (u64_stats_fetch_retry(&stats->syncp, start));
+	alloc_fail += alloc_fail_bdq;
+
+	rx->bytes = bytes;
+	rx->packets = packets;
+	rx->alloc_fail = alloc_fail;
+	rx->csum_complete = csum_complete;
+	rx->csum_none = csum_none;
+
+	fbnic_get_hw_q_stats(fbd, fbd->hw_stats.hw_q);
+
+	spin_lock(&fbd->hw_stats.lock);
+	rx->hw_drop_overruns = fbd->hw_stats.hw_q[idx].rde_pkt_cq_drop.value +
+			       fbd->hw_stats.hw_q[idx].rde_pkt_bdq_drop.value;
+	rx->hw_drops = fbd->hw_stats.hw_q[idx].rde_pkt_err.value +
+		       rx->hw_drop_overruns;
+	spin_unlock(&fbd->hw_stats.lock);
+}
+
+static void fbnic_get_queue_stats_tx(struct net_device *dev, int idx,
+				     struct netdev_queue_stats_tx *tx)
+{
+	struct fbnic_net *fbn = netdev_priv(dev);
+	struct fbnic_ring *txr = fbn->tx[idx];
+	struct fbnic_queue_stats *stats;
+	u64 stop, wake, csum, lso;
+	struct fbnic_ring *xdpr;
+	unsigned int start;
+	u64 bytes, packets;
+
+	if (!txr)
+		return;
+
+	stats = &txr->stats;
+	do {
+		start = u64_stats_fetch_begin(&stats->syncp);
+		bytes = stats->bytes;
+		packets = stats->packets;
+		csum = stats->twq.csum_partial;
+		lso = stats->twq.lso;
+		stop = stats->twq.stop;
+		wake = stats->twq.wake;
+	} while (u64_stats_fetch_retry(&stats->syncp, start));
+
+	tx->bytes = bytes;
+	tx->packets = packets;
+	tx->needs_csum = csum + lso;
+	tx->hw_gso_wire_packets = lso;
+	tx->stop = stop;
+	tx->wake = wake;
+
+	xdpr = fbn->tx[FBNIC_MAX_TXQS + idx];
+	if (xdpr) {
+		stats = &xdpr->stats;
+		do {
+			start = u64_stats_fetch_begin(&stats->syncp);
+			bytes = stats->bytes;
+			packets = stats->packets;
+		} while (u64_stats_fetch_retry(&stats->syncp, start));
+
+		tx->bytes += bytes;
+		tx->packets += packets;
+	}
+}
+
+static void fbnic_get_base_stats(struct net_device *dev,
+				 struct netdev_queue_stats_rx *rx,
+				 struct netdev_queue_stats_tx *tx)
+{
+	struct fbnic_net *fbn = netdev_priv(dev);
+
+	tx->bytes = fbn->tx_stats.bytes;
+	tx->packets = fbn->tx_stats.packets;
+	tx->needs_csum = fbn->tx_stats.twq.csum_partial + fbn->tx_stats.twq.lso;
+	tx->hw_gso_wire_packets = fbn->tx_stats.twq.lso;
+	tx->stop = fbn->tx_stats.twq.stop;
+	tx->wake = fbn->tx_stats.twq.wake;
+
+	rx->bytes = fbn->rx_stats.bytes;
+	rx->packets = fbn->rx_stats.packets;
+	rx->alloc_fail = fbn->rx_stats.rx.alloc_failed +
+		fbn->bdq_stats.bdq.alloc_failed;
+	rx->csum_complete = fbn->rx_stats.rx.csum_complete;
+	rx->csum_none = fbn->rx_stats.rx.csum_none;
+}
+
+static const struct netdev_stat_ops fbnic_stat_ops = {
+	.get_queue_stats_rx	= fbnic_get_queue_stats_rx,
+	.get_queue_stats_tx	= fbnic_get_queue_stats_tx,
+	.get_base_stats		= fbnic_get_base_stats,
+};
+
+void fbnic_reset_queues(struct fbnic_net *fbn,
+			unsigned int tx, unsigned int rx)
+{
+	struct fbnic_dev *fbd = fbn->fbd;
+	unsigned int max_napis;
+
+	max_napis = fbd->num_irqs - FBNIC_NON_NAPI_VECTORS;
+
+	tx = min(tx, max_napis);
+	fbn->num_tx_queues = tx;
+
+	rx = min(rx, max_napis);
+	fbn->num_rx_queues = rx;
+
+	fbn->num_napi = max(tx, rx);
+}
+
+/**
+ * fbnic_netdev_free - Free the netdev associate with fbnic
+ * @fbd: Driver specific structure to free netdev from
+ *
+ * Allocate and initialize the netdev and netdev private structure. Bind
+ * together the hardware, netdev, and pci data structures.
+ **/
+void fbnic_netdev_free(struct fbnic_dev *fbd)
+{
+	fbnic_phylink_destroy(fbd->netdev);
+
+	free_netdev(fbd->netdev);
+	fbd->netdev = NULL;
+}
+
+/**
+ * fbnic_netdev_alloc - Allocate a netdev and associate with fbnic
+ * @fbd: Driver specific structure to associate netdev with
+ *
+ * Allocate and initialize the netdev and netdev private structure. Bind
+ * together the hardware, netdev, and pci data structures.
+ *
+ *  Return: Pointer to net_device on success, NULL on failure
+ **/
+struct net_device *fbnic_netdev_alloc(struct fbnic_dev *fbd)
+{
+	struct net_device *netdev;
+	struct fbnic_net *fbn;
+	int default_queues;
+
+	netdev = alloc_etherdev_mq(sizeof(*fbn), FBNIC_MAX_RXQS);
+	if (!netdev)
+		return NULL;
+
+	SET_NETDEV_DEV(netdev, fbd->dev);
+	fbd->netdev = netdev;
+
+	netdev->netdev_ops = &fbnic_netdev_ops;
+	netdev->stat_ops = &fbnic_stat_ops;
+	netdev->queue_mgmt_ops = &fbnic_queue_mgmt_ops;
+	netdev->netmem_tx = NETMEM_TX_DMA;
+
+	fbnic_set_ethtool_ops(netdev);
+
+	fbn = netdev_priv(netdev);
+
+	fbn->netdev = netdev;
+	fbn->fbd = fbd;
+
+	fbn->txq_size = FBNIC_TXQ_SIZE_DEFAULT;
+	fbn->hpq_size = FBNIC_HPQ_SIZE_DEFAULT;
+	fbn->ppq_size = FBNIC_PPQ_SIZE_DEFAULT;
+	fbn->rcq_size = FBNIC_RCQ_SIZE_DEFAULT;
+
+	fbn->tx_usecs = FBNIC_TX_USECS_DEFAULT;
+	fbn->rx_usecs = FBNIC_RX_USECS_DEFAULT;
+	fbn->rx_max_frames = FBNIC_RX_FRAMES_DEFAULT;
+
+	/* Initialize the hds_thresh */
+	netdev->cfg->hds_thresh = FBNIC_HDS_THRESH_DEFAULT;
+	fbn->hds_thresh = FBNIC_HDS_THRESH_DEFAULT;
+
+	default_queues = netif_get_num_default_rss_queues();
+	if (default_queues > fbd->max_num_queues)
+		default_queues = fbd->max_num_queues;
+
+	fbnic_reset_queues(fbn, default_queues, default_queues);
+
+	fbnic_reset_indir_tbl(fbn);
+	fbnic_rss_key_fill(fbn->rss_key);
+	fbnic_rss_init_en_mask(fbn);
+
+	netdev->priv_flags |= IFF_UNICAST_FLT;
+
+	netdev->gso_partial_features =
+		NETIF_F_GSO_GRE |
+		NETIF_F_GSO_GRE_CSUM |
+		NETIF_F_GSO_IPXIP4 |
+		NETIF_F_GSO_UDP_TUNNEL |
+		NETIF_F_GSO_UDP_TUNNEL_CSUM;
+
+	netdev->features |=
+		netdev->gso_partial_features |
+		FBNIC_TUN_GSO_FEATURES |
+		NETIF_F_RXHASH |
+		NETIF_F_SG |
+		NETIF_F_HW_CSUM |
+		NETIF_F_RXCSUM |
+		NETIF_F_TSO |
+		NETIF_F_TSO_ECN |
+		NETIF_F_TSO6 |
+		NETIF_F_GSO_PARTIAL |
+		NETIF_F_GSO_UDP_L4;
+
+	netdev->hw_features |= netdev->features;
+	netdev->vlan_features |= netdev->features;
+	netdev->hw_enc_features |= netdev->features;
+	netdev->features |= NETIF_F_NTUPLE;
+
+	netdev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_RX_SG;
+
+	netdev->min_mtu = IPV6_MIN_MTU;
+	netdev->max_mtu = FBNIC_MAX_JUMBO_FRAME_SIZE - ETH_HLEN;
+
+	/* TBD: This is workaround for BMC as phylink doesn't have support
+	 * for leavling the link enabled if a BMC is present.
+	 */
+	netdev->ethtool->wol_enabled = true;
+
+	netif_carrier_off(netdev);
+
+	netif_tx_stop_all_queues(netdev);
+
+	if (fbnic_phylink_create(netdev)) {
+		free_netdev(netdev);
+		fbd->netdev = NULL;
+		return NULL;
+	}
+
+	return netdev;
+}
+
+static int fbnic_dsn_to_mac_addr(u64 dsn, char *addr)
+{
+	addr[0] = (dsn >> 56) & 0xFF;
+	addr[1] = (dsn >> 48) & 0xFF;
+	addr[2] = (dsn >> 40) & 0xFF;
+	addr[3] = (dsn >> 16) & 0xFF;
+	addr[4] = (dsn >> 8) & 0xFF;
+	addr[5] = dsn & 0xFF;
+
+	return is_valid_ether_addr(addr) ? 0 : -EINVAL;
+}
+
+/**
+ * fbnic_netdev_register - Initialize general software structures
+ * @netdev: Netdev containing structure to initialize and register
+ *
+ * Initialize the MAC address for the netdev and register it.
+ *
+ *  Return: 0 on success, negative on failure
+ **/
+int fbnic_netdev_register(struct net_device *netdev)
+{
+	struct fbnic_net *fbn = netdev_priv(netdev);
+	struct fbnic_dev *fbd = fbn->fbd;
+	u64 dsn = fbd->dsn;
+	u8 addr[ETH_ALEN];
+	int err;
+
+	err = fbnic_dsn_to_mac_addr(dsn, addr);
+	if (!err) {
+		ether_addr_copy(netdev->perm_addr, addr);
+		eth_hw_addr_set(netdev, addr);
+	} else {
+		/* A randomly assigned MAC address will cause provisioning
+		 * issues so instead just fail to spawn the netdev and
+		 * avoid any confusion.
+		 */
+		dev_err(fbd->dev, "MAC addr %pM invalid\n", addr);
+		return err;
+	}
+
+	return register_netdev(netdev);
+}
+
+void fbnic_netdev_unregister(struct net_device *netdev)
+{
+	unregister_netdev(netdev);
+}

linux-7.2.3/drivers/net/ethernet/meta/fbnic/fbnic_netdev.h

@@ -0,0 +1,119 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) Meta Platforms, Inc. and affiliates. */
+
+#ifndef _FBNIC_NETDEV_H_
+#define _FBNIC_NETDEV_H_
+
+#include <linux/phylink.h>
+#include <linux/types.h>
+
+#include "fbnic_csr.h"
+#include "fbnic_rpc.h"
+#include "fbnic_txrx.h"
+
+#define FBNIC_MAX_NAPI_VECTORS		128u
+#define FBNIC_MIN_RXD_PER_FRAME		2
+
+/* Natively supported tunnel GSO features (not thru GSO_PARTIAL) */
+#define FBNIC_TUN_GSO_FEATURES		NETIF_F_GSO_IPXIP6
+
+struct fbnic_net {
+	struct bpf_prog *xdp_prog;
+
+	struct fbnic_ring *tx[FBNIC_MAX_TXQS + FBNIC_MAX_XDPQS];
+	struct fbnic_ring *rx[FBNIC_MAX_RXQS];
+
+	struct fbnic_napi_vector *napi[FBNIC_MAX_NAPI_VECTORS];
+
+	struct net_device *netdev;
+	struct fbnic_dev *fbd;
+
+	u32 txq_size;
+	u32 hpq_size;
+	u32 ppq_size;
+	u32 rcq_size;
+
+	u32 hds_thresh;
+
+	u16 rx_usecs;
+	u16 tx_usecs;
+
+	u32 rx_max_frames;
+
+	u16 num_napi;
+
+	struct phylink *phylink;
+	struct phylink_config phylink_config;
+	struct phylink_pcs *pcs;
+
+	u8 aui;
+	u8 fec;
+
+	/* Cached top bits of the HW time counter for 40b -> 64b conversion */
+	u32 time_high;
+	/* Protect readers of @time_offset, writers take @time_lock. */
+	struct u64_stats_sync time_seq;
+	/* Offset in ns between free running NIC PHC and time set via PTP
+	 * clock callbacks
+	 */
+	s64 time_offset;
+
+	u16 num_tx_queues;
+	u16 num_rx_queues;
+
+	u8 indir_tbl[FBNIC_RPC_RSS_TBL_COUNT][FBNIC_RPC_RSS_TBL_SIZE];
+	u32 rss_key[FBNIC_RPC_RSS_KEY_DWORD_LEN];
+	u32 rss_flow_hash[FBNIC_NUM_HASH_OPT];
+
+	/* Storage for stats after ring destruction */
+	struct fbnic_queue_stats tx_stats;
+	struct fbnic_queue_stats rx_stats;
+	struct fbnic_queue_stats bdq_stats;
+	u64 link_down_events;
+
+	/* Time stamping filter config */
+	struct kernel_hwtstamp_config hwtstamp_config;
+
+	bool tx_pause;
+};
+
+int __fbnic_open(struct fbnic_net *fbn);
+void fbnic_up(struct fbnic_net *fbn);
+void fbnic_down(struct fbnic_net *fbn);
+void fbnic_down_noidle(struct fbnic_net *fbn);
+
+struct net_device *fbnic_netdev_alloc(struct fbnic_dev *fbd);
+void fbnic_netdev_free(struct fbnic_dev *fbd);
+int fbnic_netdev_register(struct net_device *netdev);
+void fbnic_netdev_unregister(struct net_device *netdev);
+void fbnic_reset_queues(struct fbnic_net *fbn,
+			unsigned int tx, unsigned int rx);
+
+void fbnic_set_ethtool_ops(struct net_device *dev);
+
+int fbnic_ptp_setup(struct fbnic_dev *fbd);
+void fbnic_ptp_destroy(struct fbnic_dev *fbd);
+void fbnic_time_init(struct fbnic_net *fbn);
+int fbnic_time_start(struct fbnic_net *fbn);
+void fbnic_time_stop(struct fbnic_net *fbn);
+
+void __fbnic_set_rx_mode(struct fbnic_dev *fbd,
+			 struct netdev_hw_addr_list *uc,
+			 struct netdev_hw_addr_list *mc);
+void fbnic_clear_rx_mode(struct fbnic_dev *fbd);
+
+void fbnic_phylink_get_pauseparam(struct net_device *netdev,
+				  struct ethtool_pauseparam *pause);
+int fbnic_phylink_set_pauseparam(struct net_device *netdev,
+				 struct ethtool_pauseparam *pause);
+int fbnic_phylink_ethtool_ksettings_get(struct net_device *netdev,
+					struct ethtool_link_ksettings *cmd);
+int fbnic_phylink_get_fecparam(struct net_device *netdev,
+			       struct ethtool_fecparam *fecparam);
+int fbnic_phylink_create(struct net_device *netdev);
+void fbnic_phylink_destroy(struct net_device *netdev);
+int fbnic_phylink_init(struct net_device *netdev);
+void fbnic_phylink_pmd_training_complete_notify(struct net_device *netdev);
+bool fbnic_check_split_frames(struct bpf_prog *prog,
+			      unsigned int mtu, u32 hds_threshold);
+#endif /* _FBNIC_NETDEV_H_ */

linux-7.2.3/drivers/net/ethernet/meta/fbnic/fbnic_pci.c

@@ -0,0 +1,673 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) Meta Platforms, Inc. and affiliates. */
+
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/pci.h>
+#include <linux/rtnetlink.h>
+#include <linux/types.h>
+#include <net/devlink.h>
+
+#include "fbnic.h"
+#include "fbnic_drvinfo.h"
+#include "fbnic_hw_stats.h"
+#include "fbnic_netdev.h"
+
+char fbnic_driver_name[] = DRV_NAME;
+
+MODULE_DESCRIPTION(DRV_SUMMARY);
+MODULE_LICENSE("GPL");
+
+static const struct fbnic_info fbnic_asic_info = {
+	.max_num_queues = FBNIC_MAX_QUEUES,
+	.bar_mask = BIT(0) | BIT(4)
+};
+
+static const struct fbnic_info *fbnic_info_tbl[] = {
+	[fbnic_board_asic] = &fbnic_asic_info,
+};
+
+static const struct pci_device_id fbnic_pci_tbl[] = {
+	{ PCI_DEVICE_DATA(META, FBNIC_ASIC, fbnic_board_asic) },
+	/* Required last entry */
+	{0, }
+};
+MODULE_DEVICE_TABLE(pci, fbnic_pci_tbl);
+
+u32 fbnic_rd32(struct fbnic_dev *fbd, u32 reg)
+{
+	u32 __iomem *csr = READ_ONCE(fbd->uc_addr0);
+	u32 value;
+
+	if (!csr)
+		return ~0U;
+
+	value = readl(csr + reg);
+
+	/* If any bits are 0 value should be valid */
+	if (~value)
+		return value;
+
+	/* All 1's may be valid if ZEROs register still works */
+	if (reg != FBNIC_MASTER_SPARE_0 && ~readl(csr + FBNIC_MASTER_SPARE_0))
+		return value;
+
+	/* Hardware is giving us all 1's reads, assume it is gone */
+	WRITE_ONCE(fbd->uc_addr0, NULL);
+	WRITE_ONCE(fbd->uc_addr4, NULL);
+
+	dev_err(fbd->dev,
+		"Failed read (idx 0x%x AKA addr 0x%x), disabled CSR access, awaiting reset\n",
+		reg, reg << 2);
+
+	/* Notify stack that device has lost (PCIe) link */
+	if (!fbnic_init_failure(fbd))
+		netif_device_detach(fbd->netdev);
+
+	return ~0U;
+}
+
+bool fbnic_fw_present(struct fbnic_dev *fbd)
+{
+	return !!READ_ONCE(fbd->uc_addr4);
+}
+
+void fbnic_fw_wr32(struct fbnic_dev *fbd, u32 reg, u32 val)
+{
+	u32 __iomem *csr = READ_ONCE(fbd->uc_addr4);
+
+	if (csr)
+		writel(val, csr + reg);
+}
+
+u32 fbnic_fw_rd32(struct fbnic_dev *fbd, u32 reg)
+{
+	u32 __iomem *csr = READ_ONCE(fbd->uc_addr4);
+	u32 value;
+
+	if (!csr)
+		return ~0U;
+
+	value = readl(csr + reg);
+
+	/* If any bits are 0 value should be valid */
+	if (~value)
+		return value;
+
+	/* All 1's may be valid if ZEROs register still works */
+	if (reg != FBNIC_FW_ZERO_REG && ~readl(csr + FBNIC_FW_ZERO_REG))
+		return value;
+
+	/* Hardware is giving us all 1's reads, assume it is gone */
+	WRITE_ONCE(fbd->uc_addr0, NULL);
+	WRITE_ONCE(fbd->uc_addr4, NULL);
+
+	dev_err(fbd->dev,
+		"Failed read (idx 0x%x AKA addr 0x%x), disabled CSR access, awaiting reset\n",
+		reg, reg << 2);
+
+	/* Notify stack that device has lost (PCIe) link */
+	if (!fbnic_init_failure(fbd))
+		netif_device_detach(fbd->netdev);
+
+	return ~0U;
+}
+
+static void fbnic_service_task_start(struct fbnic_net *fbn)
+{
+	struct fbnic_dev *fbd = fbn->fbd;
+
+	schedule_delayed_work(&fbd->service_task, HZ);
+}
+
+static void fbnic_service_task_stop(struct fbnic_net *fbn)
+{
+	struct fbnic_dev *fbd = fbn->fbd;
+
+	cancel_delayed_work(&fbd->service_task);
+}
+
+void fbnic_up(struct fbnic_net *fbn)
+{
+	fbnic_enable(fbn);
+
+	fbnic_fill(fbn);
+
+	fbnic_rss_reinit_hw(fbn->fbd, fbn);
+
+	netif_addr_lock_bh(fbn->netdev);
+	__fbnic_set_rx_mode(fbn->fbd, &fbn->netdev->uc, &fbn->netdev->mc);
+	netif_addr_unlock_bh(fbn->netdev);
+
+	/* Enable Tx/Rx processing */
+	fbnic_napi_enable(fbn);
+	netif_tx_wake_all_queues(fbn->netdev);
+
+	fbnic_service_task_start(fbn);
+
+	fbnic_dbg_up(fbn);
+}
+
+void fbnic_down_noidle(struct fbnic_net *fbn)
+{
+	fbnic_dbg_down(fbn);
+
+	fbnic_service_task_stop(fbn);
+
+	/* Disable Tx/Rx Processing */
+	fbnic_napi_disable(fbn);
+	netif_tx_disable(fbn->netdev);
+
+	fbnic_clear_rx_mode(fbn->fbd);
+	fbnic_clear_rules(fbn->fbd);
+	fbnic_rss_disable_hw(fbn->fbd);
+	fbnic_disable(fbn);
+}
+
+void fbnic_down(struct fbnic_net *fbn)
+{
+	fbnic_down_noidle(fbn);
+
+	fbnic_wait_all_queues_idle(fbn->fbd, false);
+
+	fbnic_flush(fbn);
+}
+
+static int fbnic_fw_config_after_crash(struct fbnic_dev *fbd)
+{
+	if (fbnic_fw_xmit_ownership_msg(fbd, true)) {
+		dev_err(fbd->dev, "NIC failed to take ownership\n");
+
+		return -1;
+	}
+
+	fbnic_rpc_reset_valid_entries(fbd);
+	netif_addr_lock_bh(fbd->netdev);
+	__fbnic_set_rx_mode(fbd, &fbd->netdev->uc, &fbd->netdev->mc);
+	netif_addr_unlock_bh(fbd->netdev);
+
+	return 0;
+}
+
+static void fbnic_health_check(struct fbnic_dev *fbd)
+{
+	struct fbnic_fw_mbx *tx_mbx = &fbd->mbx[FBNIC_IPC_MBX_TX_IDX];
+
+	/* As long as the heart is beating the FW is healthy */
+	if (fbd->fw_heartbeat_enabled)
+		return;
+
+	/* If the Tx mailbox still has messages sitting in it then there likely
+	 * isn't anything we can do. We will wait until the mailbox is empty to
+	 * report the fault so we can collect the crashlog.
+	 */
+	if (tx_mbx->head != tx_mbx->tail)
+		return;
+
+	fbnic_devlink_fw_report(fbd, "Firmware crash detected!");
+	fbnic_devlink_otp_check(fbd, "error detected after firmware recovery");
+
+	if (fbnic_fw_config_after_crash(fbd))
+		dev_err(fbd->dev, "Firmware recovery failed after crash\n");
+}
+
+static void fbnic_service_task(struct work_struct *work)
+{
+	struct fbnic_dev *fbd = container_of(to_delayed_work(work),
+					     struct fbnic_dev, service_task);
+	struct net_device *netdev = fbd->netdev;
+
+	if (netif_running(netdev))
+		fbnic_phylink_pmd_training_complete_notify(netdev);
+
+	rtnl_lock();
+
+	fbnic_get_hw_stats32(fbd);
+
+	if (fbd->ps_timeout && fbnic_mac_check_tx_pause(fbd))
+		fbnic_mac_ps_protect_handler(fbd);
+
+	fbnic_fw_check_heartbeat(fbd);
+
+	fbnic_health_check(fbd);
+
+	fbnic_bmc_rpc_check(fbd);
+
+	if (netif_carrier_ok(fbd->netdev)) {
+		netdev_lock(fbd->netdev);
+		fbnic_napi_depletion_check(fbd->netdev);
+		netdev_unlock(fbd->netdev);
+	}
+
+	if (netif_running(netdev))
+		schedule_delayed_work(&fbd->service_task, HZ);
+
+	rtnl_unlock();
+}
+
+/**
+ * fbnic_probe - Device Initialization Routine
+ * @pdev: PCI device information struct
+ * @ent: entry in fbnic_pci_tbl
+ *
+ * Initializes a PCI device identified by a pci_dev structure.
+ * The OS initialization, configuring of the adapter private structure,
+ * and a hardware reset occur.
+ *
+ * Return: 0 on success, negative on failure
+ **/
+static int fbnic_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
+{
+	const struct fbnic_info *info = fbnic_info_tbl[ent->driver_data];
+	struct net_device *netdev;
+	struct fbnic_dev *fbd;
+	int err;
+
+	if (pdev->error_state != pci_channel_io_normal) {
+		dev_err(&pdev->dev,
+			"PCI device still in an error state. Unable to load...\n");
+		return -EIO;
+	}
+
+	err = pcim_enable_device(pdev);
+	if (err) {
+		dev_err(&pdev->dev, "PCI enable device failed: %d\n", err);
+		return err;
+	}
+
+	err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(46));
+	if (err)
+		err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32));
+	if (err) {
+		dev_err(&pdev->dev, "DMA configuration failed: %d\n", err);
+		return err;
+	}
+
+	err = pcim_iomap_regions(pdev, info->bar_mask, fbnic_driver_name);
+	if (err) {
+		dev_err(&pdev->dev,
+			"pci_request_selected_regions failed: %d\n", err);
+		return err;
+	}
+
+	fbd = fbnic_devlink_alloc(pdev);
+	if (!fbd) {
+		dev_err(&pdev->dev, "Devlink allocation failed\n");
+		return -ENOMEM;
+	}
+
+	err = fbnic_devlink_health_create(fbd);
+	if (err)
+		goto free_fbd;
+
+	/* Populate driver with hardware-specific info and handlers */
+	fbd->max_num_queues = info->max_num_queues;
+
+	fbd->ps_timeout = FBNIC_MAC_PS_TO_DEFAULT_MS;
+
+	pci_set_master(pdev);
+	pci_save_state(pdev);
+
+	INIT_DELAYED_WORK(&fbd->service_task, fbnic_service_task);
+
+	err = fbnic_alloc_irqs(fbd);
+	if (err)
+		goto err_destroy_health;
+
+	err = fbnic_mac_init(fbd);
+	if (err) {
+		dev_err(&pdev->dev, "Failed to initialize MAC: %d\n", err);
+		goto free_irqs;
+	}
+
+	err = fbnic_fw_log_init(fbd);
+	if (err)
+		dev_warn(fbd->dev,
+			 "Unable to initialize firmware log buffer: %d\n",
+			 err);
+
+	err = fbnic_fw_request_mbx(fbd);
+	if (err) {
+		dev_err(&pdev->dev,
+			"Firmware mailbox initialization failure\n");
+		goto free_fw_log;
+	}
+
+	/* Send the request to enable the FW logging to host. Note if this
+	 * fails we ignore the error and just display a message as it is
+	 * possible the FW is just too old to support the logging and needs
+	 * to be updated.
+	 */
+	fbnic_fw_log_enable(fbd, true);
+
+	fbnic_devlink_register(fbd);
+	fbnic_devlink_otp_check(fbd, "error detected during probe");
+	fbnic_dbg_fbd_init(fbd);
+
+	/* Capture snapshot of hardware stats so netdev can calculate delta */
+	fbnic_init_hw_stats(fbd);
+
+	fbnic_hwmon_register(fbd);
+
+	if (!fbd->dsn) {
+		dev_warn(&pdev->dev, "Reading serial number failed\n");
+		goto init_failure_mode;
+	}
+
+	if (fbnic_mdiobus_create(fbd))
+		goto init_failure_mode;
+
+	netdev = fbnic_netdev_alloc(fbd);
+	if (!netdev) {
+		dev_err(&pdev->dev, "Netdev allocation failed\n");
+		goto init_failure_mode;
+	}
+
+	err = fbnic_ptp_setup(fbd);
+	if (err)
+		goto ifm_free_netdev;
+
+	err = fbnic_netdev_register(netdev);
+	if (err) {
+		dev_err(&pdev->dev, "Netdev registration failed: %d\n", err);
+		goto ifm_destroy_ptp;
+	}
+
+	return 0;
+
+ifm_destroy_ptp:
+	fbnic_ptp_destroy(fbd);
+ifm_free_netdev:
+	fbnic_netdev_free(fbd);
+init_failure_mode:
+	dev_warn(&pdev->dev, "Probe error encountered, entering init failure mode. Normal networking functionality will not be available.\n");
+	 /* Always return 0 even on error so devlink is registered to allow
+	  * firmware updates for fixes.
+	  */
+	return 0;
+free_fw_log:
+	fbnic_fw_log_free(fbd);
+free_irqs:
+	fbnic_free_irqs(fbd);
+err_destroy_health:
+	fbnic_devlink_health_destroy(fbd);
+free_fbd:
+	fbnic_devlink_free(fbd);
+
+	return err;
+}
+
+/**
+ * fbnic_remove - Device Removal Routine
+ * @pdev: PCI device information struct
+ *
+ * Called by the PCI subsystem to alert the driver that it should release
+ * a PCI device.  This could be caused by a Hot-Plug event, or because the
+ * driver is going to be removed from memory.
+ **/
+static void fbnic_remove(struct pci_dev *pdev)
+{
+	struct fbnic_dev *fbd = pci_get_drvdata(pdev);
+
+	if (!fbnic_init_failure(fbd)) {
+		struct net_device *netdev = fbd->netdev;
+
+		fbnic_netdev_unregister(netdev);
+		cancel_delayed_work_sync(&fbd->service_task);
+		fbnic_ptp_destroy(fbd);
+		fbnic_netdev_free(fbd);
+	}
+
+	fbnic_hwmon_unregister(fbd);
+	fbnic_dbg_fbd_exit(fbd);
+	fbnic_devlink_unregister(fbd);
+	fbnic_fw_log_disable(fbd);
+	fbnic_fw_free_mbx(fbd);
+	fbnic_fw_log_free(fbd);
+	fbnic_free_irqs(fbd);
+
+	fbnic_devlink_health_destroy(fbd);
+	fbnic_devlink_free(fbd);
+}
+
+static int fbnic_pm_suspend(struct device *dev)
+{
+	struct fbnic_dev *fbd = dev_get_drvdata(dev);
+	struct net_device *netdev = fbd->netdev;
+
+	if (fbnic_init_failure(fbd))
+		goto null_uc_addr;
+
+	rtnl_lock();
+	netdev_lock(netdev);
+
+	netif_device_detach(netdev);
+
+	if (netif_running(netdev))
+		netdev->netdev_ops->ndo_stop(netdev);
+
+	netdev_unlock(netdev);
+	rtnl_unlock();
+
+null_uc_addr:
+	fbnic_fw_log_disable(fbd);
+
+	devl_lock(priv_to_devlink(fbd));
+
+	fbnic_fw_free_mbx(fbd);
+
+	devl_unlock(priv_to_devlink(fbd));
+
+	/* Free the IRQs so they aren't trying to occupy sleeping CPUs */
+	fbnic_free_irqs(fbd);
+
+	/* Hardware is about to go away, so switch off MMIO access internally */
+	WRITE_ONCE(fbd->uc_addr0, NULL);
+	WRITE_ONCE(fbd->uc_addr4, NULL);
+
+	return 0;
+}
+
+static int __fbnic_pm_resume(struct device *dev)
+{
+	struct fbnic_dev *fbd = dev_get_drvdata(dev);
+	struct net_device *netdev = fbd->netdev;
+	void __iomem * const *iomap_table;
+	struct fbnic_net *fbn;
+	int err;
+
+	/* Restore MMIO access */
+	iomap_table = pcim_iomap_table(to_pci_dev(dev));
+	fbd->uc_addr0 = iomap_table[0];
+	fbd->uc_addr4 = iomap_table[4];
+
+	/* Rerequest the IRQs */
+	err = fbnic_alloc_irqs(fbd);
+	if (err)
+		goto err_invalidate_uc_addr;
+
+	fbd->mac->init_regs(fbd);
+
+	devl_lock(priv_to_devlink(fbd));
+
+	/* Re-enable mailbox */
+	err = fbnic_fw_request_mbx(fbd);
+	devl_unlock(priv_to_devlink(fbd));
+	if (err)
+		goto err_free_irqs;
+
+	/* Only send log history if log buffer is empty to prevent duplicate
+	 * log entries.
+	 */
+	fbnic_fw_log_enable(fbd, list_empty(&fbd->fw_log.entries));
+
+	/* Since the FW should be up, check if it reported OTP errors */
+	fbnic_devlink_otp_check(fbd, "error detected after PM resume");
+
+	/* No netdev means there isn't a network interface to bring up */
+	if (fbnic_init_failure(fbd))
+		return 0;
+
+	fbn = netdev_priv(netdev);
+
+	/* Reset the queues if needed */
+	fbnic_reset_queues(fbn, fbn->num_tx_queues, fbn->num_rx_queues);
+
+	rtnl_lock();
+	netdev_lock(netdev);
+
+	if (netif_running(netdev))
+		err = __fbnic_open(fbn);
+
+	netdev_unlock(netdev);
+	rtnl_unlock();
+	if (err)
+		goto err_free_mbx;
+
+	return 0;
+err_free_mbx:
+	fbnic_fw_log_disable(fbd);
+
+	devl_lock(priv_to_devlink(fbd));
+	fbnic_fw_free_mbx(fbd);
+	devl_unlock(priv_to_devlink(fbd));
+err_free_irqs:
+	fbnic_free_irqs(fbd);
+err_invalidate_uc_addr:
+	WRITE_ONCE(fbd->uc_addr0, NULL);
+	WRITE_ONCE(fbd->uc_addr4, NULL);
+	return err;
+}
+
+static void __fbnic_pm_attach(struct device *dev)
+{
+	struct fbnic_dev *fbd = dev_get_drvdata(dev);
+	struct net_device *netdev = fbd->netdev;
+	struct fbnic_net *fbn;
+
+	rtnl_lock();
+	fbnic_reset_hw_stats(fbd);
+	rtnl_unlock();
+
+	if (fbnic_init_failure(fbd))
+		return;
+
+	fbn = netdev_priv(netdev);
+
+	if (netif_running(netdev))
+		fbnic_up(fbn);
+
+	netif_device_attach(netdev);
+}
+
+static int __maybe_unused fbnic_pm_resume(struct device *dev)
+{
+	int err;
+
+	err = __fbnic_pm_resume(dev);
+	if (!err)
+		__fbnic_pm_attach(dev);
+
+	return err;
+}
+
+static const struct dev_pm_ops fbnic_pm_ops = {
+	SET_SYSTEM_SLEEP_PM_OPS(fbnic_pm_suspend, fbnic_pm_resume)
+};
+
+static void fbnic_shutdown(struct pci_dev *pdev)
+{
+	fbnic_pm_suspend(&pdev->dev);
+}
+
+static pci_ers_result_t fbnic_err_error_detected(struct pci_dev *pdev,
+						 pci_channel_state_t state)
+{
+	/* Disconnect device if failure is not recoverable via reset */
+	if (state == pci_channel_io_perm_failure)
+		return PCI_ERS_RESULT_DISCONNECT;
+
+	fbnic_pm_suspend(&pdev->dev);
+
+	/* Request a slot reset */
+	return PCI_ERS_RESULT_NEED_RESET;
+}
+
+static pci_ers_result_t fbnic_err_slot_reset(struct pci_dev *pdev)
+{
+	int err;
+
+	pci_set_power_state(pdev, PCI_D0);
+	pci_restore_state(pdev);
+
+	if (pci_enable_device_mem(pdev)) {
+		dev_err(&pdev->dev,
+			"Cannot re-enable PCI device after reset.\n");
+		return PCI_ERS_RESULT_DISCONNECT;
+	}
+
+	/* Restore device to previous state */
+	err = __fbnic_pm_resume(&pdev->dev);
+
+	return err ? PCI_ERS_RESULT_DISCONNECT : PCI_ERS_RESULT_RECOVERED;
+}
+
+static void fbnic_err_resume(struct pci_dev *pdev)
+{
+	__fbnic_pm_attach(&pdev->dev);
+}
+
+static const struct pci_error_handlers fbnic_err_handler = {
+	.error_detected	= fbnic_err_error_detected,
+	.slot_reset	= fbnic_err_slot_reset,
+	.resume		= fbnic_err_resume,
+};
+
+static struct pci_driver fbnic_driver = {
+	.name		= fbnic_driver_name,
+	.id_table	= fbnic_pci_tbl,
+	.probe		= fbnic_probe,
+	.remove		= fbnic_remove,
+	.driver.pm	= &fbnic_pm_ops,
+	.shutdown	= fbnic_shutdown,
+	.err_handler	= &fbnic_err_handler,
+};
+
+/**
+ * fbnic_init_module - Driver Registration Routine
+ *
+ * The first routine called when the driver is loaded.  All it does is
+ * register with the PCI subsystem.
+ *
+ * Return: 0 on success, negative on failure
+ **/
+static int __init fbnic_init_module(void)
+{
+	int err;
+
+	fbnic_dbg_init();
+
+	err = pci_register_driver(&fbnic_driver);
+	if (err) {
+		fbnic_dbg_exit();
+		goto out;
+	}
+
+	pr_info(DRV_SUMMARY " (%s)", fbnic_driver.name);
+out:
+	return err;
+}
+module_init(fbnic_init_module);
+
+/**
+ * fbnic_exit_module - Driver Exit Cleanup Routine
+ *
+ * Called just before the driver is removed from memory.
+ **/
+static void __exit fbnic_exit_module(void)
+{
+	pci_unregister_driver(&fbnic_driver);
+
+	fbnic_dbg_exit();
+}
+module_exit(fbnic_exit_module);

linux-7.2.3/drivers/net/ethernet/meta/fbnic/fbnic_phylink.c

@@ -0,0 +1,311 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) Meta Platforms, Inc. and affiliates. */
+
+#include <linux/pcs/pcs-xpcs.h>
+#include <linux/phy.h>
+#include <linux/phylink.h>
+
+#include "fbnic.h"
+#include "fbnic_mac.h"
+#include "fbnic_netdev.h"
+
+static phy_interface_t fbnic_phylink_select_interface(u8 aui)
+{
+	switch (aui) {
+	case FBNIC_AUI_100GAUI2:
+		return PHY_INTERFACE_MODE_100GBASEP;
+	case FBNIC_AUI_50GAUI1:
+		return PHY_INTERFACE_MODE_50GBASER;
+	case FBNIC_AUI_LAUI2:
+		return PHY_INTERFACE_MODE_LAUI;
+	case FBNIC_AUI_25GAUI:
+		return PHY_INTERFACE_MODE_25GBASER;
+	}
+
+	return PHY_INTERFACE_MODE_NA;
+}
+
+void fbnic_phylink_get_pauseparam(struct net_device *netdev,
+				  struct ethtool_pauseparam *pause)
+{
+	struct fbnic_net *fbn = netdev_priv(netdev);
+
+	phylink_ethtool_get_pauseparam(fbn->phylink, pause);
+}
+
+int fbnic_phylink_set_pauseparam(struct net_device *netdev,
+				 struct ethtool_pauseparam *pause)
+{
+	struct fbnic_net *fbn = netdev_priv(netdev);
+
+	return phylink_ethtool_set_pauseparam(fbn->phylink, pause);
+}
+
+static void
+fbnic_phylink_get_supported_fec_modes(unsigned long *supported)
+{
+	/* The NIC can support up to 8 possible combinations.
+	 * Either 50G-CR, or 100G-CR2
+	 *   This is with RS FEC mode only
+	 * Either 25G-CR, or 50G-CR2
+	 *   This is with No FEC, RS, or Base-R
+	 */
+	if (phylink_test(supported, 100000baseCR2_Full) ||
+	    phylink_test(supported, 50000baseCR_Full))
+		phylink_set(supported, FEC_RS);
+	if (phylink_test(supported, 50000baseCR2_Full) ||
+	    phylink_test(supported, 25000baseCR_Full)) {
+		phylink_set(supported, FEC_BASER);
+		phylink_set(supported, FEC_NONE);
+		phylink_set(supported, FEC_RS);
+	}
+}
+
+int fbnic_phylink_ethtool_ksettings_get(struct net_device *netdev,
+					struct ethtool_link_ksettings *cmd)
+{
+	struct fbnic_net *fbn = netdev_priv(netdev);
+	int err;
+
+	err = phylink_ethtool_ksettings_get(fbn->phylink, cmd);
+	if (!err) {
+		unsigned long *supp = cmd->link_modes.supported;
+
+		cmd->base.port = PORT_DA;
+		cmd->lanes = (fbn->aui & FBNIC_AUI_MODE_R2) ? 2 : 1;
+
+		fbnic_phylink_get_supported_fec_modes(supp);
+	}
+
+	return err;
+}
+
+int fbnic_phylink_get_fecparam(struct net_device *netdev,
+			       struct ethtool_fecparam *fecparam)
+{
+	struct fbnic_net *fbn = netdev_priv(netdev);
+
+	if (fbn->fec & FBNIC_FEC_RS) {
+		fecparam->active_fec = ETHTOOL_FEC_RS;
+		fecparam->fec = ETHTOOL_FEC_RS;
+	} else if (fbn->fec & FBNIC_FEC_BASER) {
+		fecparam->active_fec = ETHTOOL_FEC_BASER;
+		fecparam->fec = ETHTOOL_FEC_BASER;
+	} else {
+		fecparam->active_fec = ETHTOOL_FEC_OFF;
+		fecparam->fec = ETHTOOL_FEC_OFF;
+	}
+
+	if (fbn->aui & FBNIC_AUI_MODE_PAM4)
+		fecparam->fec |= ETHTOOL_FEC_AUTO;
+
+	return 0;
+}
+
+static struct phylink_pcs *
+fbnic_phylink_mac_select_pcs(struct phylink_config *config,
+			     phy_interface_t interface)
+{
+	struct net_device *netdev = to_net_dev(config->dev);
+	struct fbnic_net *fbn = netdev_priv(netdev);
+
+	return fbn->pcs;
+}
+
+static int
+fbnic_phylink_mac_prepare(struct phylink_config *config, unsigned int mode,
+			  phy_interface_t iface)
+{
+	struct net_device *netdev = to_net_dev(config->dev);
+	struct fbnic_net *fbn = netdev_priv(netdev);
+	struct fbnic_dev *fbd = fbn->fbd;
+
+	fbd->mac->prepare(fbd, fbn->aui, fbn->fec);
+
+	return 0;
+}
+
+static void
+fbnic_phylink_mac_config(struct phylink_config *config, unsigned int mode,
+			 const struct phylink_link_state *state)
+{
+}
+
+static int
+fbnic_phylink_mac_finish(struct phylink_config *config, unsigned int mode,
+			 phy_interface_t iface)
+{
+	struct net_device *netdev = to_net_dev(config->dev);
+	struct fbnic_net *fbn = netdev_priv(netdev);
+	struct fbnic_dev *fbd = fbn->fbd;
+
+	/* Retest the link state and restart interrupts */
+	fbd->mac->get_link(fbd, fbn->aui, fbn->fec);
+
+	return 0;
+}
+
+static void
+fbnic_phylink_mac_link_down(struct phylink_config *config, unsigned int mode,
+			    phy_interface_t interface)
+{
+	struct net_device *netdev = to_net_dev(config->dev);
+	struct fbnic_net *fbn = netdev_priv(netdev);
+	struct fbnic_dev *fbd = fbn->fbd;
+
+	fbd->mac->link_down(fbd);
+
+	fbn->link_down_events++;
+}
+
+static void
+fbnic_phylink_mac_link_up(struct phylink_config *config,
+			  struct phy_device *phy, unsigned int mode,
+			  phy_interface_t interface, int speed, int duplex,
+			  bool tx_pause, bool rx_pause)
+{
+	struct net_device *netdev = to_net_dev(config->dev);
+	struct fbnic_net *fbn = netdev_priv(netdev);
+	struct fbnic_dev *fbd = fbn->fbd;
+
+	fbn->tx_pause = tx_pause;
+	fbnic_config_drop_mode(fbn, tx_pause);
+
+	fbd->mac->link_up(fbd, tx_pause, rx_pause);
+}
+
+static const struct phylink_mac_ops fbnic_phylink_mac_ops = {
+	.mac_select_pcs = fbnic_phylink_mac_select_pcs,
+	.mac_prepare = fbnic_phylink_mac_prepare,
+	.mac_config = fbnic_phylink_mac_config,
+	.mac_finish = fbnic_phylink_mac_finish,
+	.mac_link_down = fbnic_phylink_mac_link_down,
+	.mac_link_up = fbnic_phylink_mac_link_up,
+};
+
+/**
+ * fbnic_phylink_create - Phylink device creation
+ * @netdev: Network Device struct to attach phylink device
+ *
+ * Initialize and attach a phylink instance to the device. The phylink
+ * device will make use of the netdev struct to track carrier and will
+ * eventually be used to expose the current state of the MAC and PCS
+ * setup.
+ *
+ * Return: 0 on success, negative on failure
+ **/
+int fbnic_phylink_create(struct net_device *netdev)
+{
+	struct fbnic_net *fbn = netdev_priv(netdev);
+	struct fbnic_dev *fbd = fbn->fbd;
+	struct phylink_pcs *pcs;
+	struct phylink *phylink;
+	int err;
+
+	pcs = xpcs_create_pcs_mdiodev(fbd->mdio_bus, 0);
+	if (IS_ERR(pcs)) {
+		err = PTR_ERR(pcs);
+		dev_err(fbd->dev, "Failed to create PCS device: %d\n", err);
+		return err;
+	}
+
+	fbn->pcs = pcs;
+
+	fbn->phylink_config.dev = &netdev->dev;
+	fbn->phylink_config.type = PHYLINK_NETDEV;
+	fbn->phylink_config.mac_capabilities = MAC_SYM_PAUSE | MAC_ASYM_PAUSE |
+					       MAC_25000FD | MAC_50000FD |
+					       MAC_100000FD;
+	fbn->phylink_config.default_an_inband = true;
+
+	__set_bit(PHY_INTERFACE_MODE_100GBASEP,
+		  fbn->phylink_config.supported_interfaces);
+	__set_bit(PHY_INTERFACE_MODE_50GBASER,
+		  fbn->phylink_config.supported_interfaces);
+	__set_bit(PHY_INTERFACE_MODE_LAUI,
+		  fbn->phylink_config.supported_interfaces);
+	__set_bit(PHY_INTERFACE_MODE_25GBASER,
+		  fbn->phylink_config.supported_interfaces);
+
+	fbnic_mac_get_fw_settings(fbd, &fbn->aui, &fbn->fec);
+
+	phylink = phylink_create(&fbn->phylink_config, NULL,
+				 fbnic_phylink_select_interface(fbn->aui),
+				 &fbnic_phylink_mac_ops);
+	if (IS_ERR(phylink)) {
+		err = PTR_ERR(phylink);
+		dev_err(netdev->dev.parent,
+			"Failed to create Phylink interface, err: %d\n", err);
+		xpcs_destroy_pcs(pcs);
+		return err;
+	}
+
+	fbn->phylink = phylink;
+
+	return 0;
+}
+
+/**
+ * fbnic_phylink_destroy - Teardown phylink related interfaces
+ * @netdev: Network Device struct containing phylink device
+ *
+ * Detach and free resources related to phylink interface.
+ **/
+void fbnic_phylink_destroy(struct net_device *netdev)
+{
+	struct fbnic_net *fbn = netdev_priv(netdev);
+
+	if (fbn->phylink)
+		phylink_destroy(fbn->phylink);
+	if (fbn->pcs)
+		xpcs_destroy_pcs(fbn->pcs);
+}
+
+/**
+ * fbnic_phylink_pmd_training_complete_notify - PMD training complete notifier
+ * @netdev: Netdev struct phylink device attached to
+ *
+ * When the link first comes up the PMD will have a period of 2 to 3 seconds
+ * where the link will flutter due to link training. To avoid spamming the
+ * kernel log with messages about this we add a delay of 4 seconds from the
+ * time of the last PCS report of link so that we can guarantee we are unlikely
+ * to see any further link loss events due to link training.
+ **/
+void fbnic_phylink_pmd_training_complete_notify(struct net_device *netdev)
+{
+	struct fbnic_net *fbn = netdev_priv(netdev);
+	struct fbnic_dev *fbd = fbn->fbd;
+
+	if (fbd->pmd_state != FBNIC_PMD_TRAINING)
+		return;
+
+	/* Prevent reading end_of_pmd_training until we verified state */
+	smp_rmb();
+
+	if (!time_before(READ_ONCE(fbd->end_of_pmd_training), jiffies))
+		return;
+
+	/* At this point we have verified that the link has been up for
+	 * the full training duration. As a first step we will try
+	 * transitioning to link ready.
+	 */
+	if (cmpxchg(&fbd->pmd_state, FBNIC_PMD_TRAINING,
+		    FBNIC_PMD_LINK_READY) != FBNIC_PMD_TRAINING)
+		return;
+
+	/* Perform a follow-up check to verify that the link didn't flap
+	 * just before our transition by rechecking the training timer.
+	 */
+	if (!time_before(READ_ONCE(fbd->end_of_pmd_training), jiffies))
+		return;
+
+	/* The training timeout has been completed. We are good to swap out
+	 * link_ready for send_data assuming no other events have occurred
+	 * that would have pulled us back into initialization or training.
+	 */
+	if (cmpxchg(&fbd->pmd_state, FBNIC_PMD_LINK_READY,
+		    FBNIC_PMD_SEND_DATA) != FBNIC_PMD_LINK_READY)
+		return;
+
+	phylink_pcs_change(fbn->pcs, false);
+}

linux-7.2.3/drivers/net/ethernet/meta/fbnic/fbnic_rpc.h

@@ -0,0 +1,232 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) Meta Platforms, Inc. and affiliates. */
+
+#ifndef _FBNIC_RPC_H_
+#define _FBNIC_RPC_H_
+
+#include <uapi/linux/in6.h>
+#include <linux/bitfield.h>
+
+struct in_addr;
+
+/*  The TCAM state definitions follow an expected ordering.
+ *  They start out disabled, then move through the following states:
+ *  Disabled  0	-> Add	      2
+ *  Add	      2	-> Valid      1
+ *
+ *  Valid     1	-> Add/Update 2
+ *  Add	      2	-> Valid      1
+ *
+ *  Valid     1	-> Delete     3
+ *  Delete    3	-> Disabled   0
+ */
+enum {
+	FBNIC_TCAM_S_DISABLED	= 0,
+	FBNIC_TCAM_S_VALID	= 1,
+	FBNIC_TCAM_S_ADD	= 2,
+	FBNIC_TCAM_S_UPDATE	= FBNIC_TCAM_S_ADD,
+	FBNIC_TCAM_S_DELETE	= 3,
+};
+
+/* 32 MAC Destination Address TCAM Entries
+ * 4 registers DA[1:0], DA[3:2], DA[5:4], Validate
+ */
+#define FBNIC_RPC_TCAM_MACDA_WORD_LEN		3
+#define FBNIC_RPC_TCAM_MACDA_NUM_ENTRIES	32
+
+/* 8 IPSRC and IPDST TCAM Entries each
+ * 8 registers, Validate each
+ */
+#define FBNIC_RPC_TCAM_IP_ADDR_WORD_LEN		8
+#define FBNIC_RPC_TCAM_IP_ADDR_NUM_ENTRIES	8
+
+#define FBNIC_RPC_TCAM_ACT_WORD_LEN		11
+#define FBNIC_RPC_TCAM_ACT_NUM_ENTRIES		64
+
+#define FBNIC_TCE_TCAM_WORD_LEN			3
+#define FBNIC_TCE_TCAM_NUM_ENTRIES		8
+
+struct fbnic_mac_addr {
+	union {
+		unsigned char addr8[ETH_ALEN];
+		__be16 addr16[FBNIC_RPC_TCAM_MACDA_WORD_LEN];
+	} mask, value;
+	unsigned char state;
+	DECLARE_BITMAP(act_tcam, FBNIC_RPC_TCAM_ACT_NUM_ENTRIES);
+};
+
+struct fbnic_ip_addr {
+	struct in6_addr mask, value;
+	unsigned char version;
+	unsigned char state;
+	DECLARE_BITMAP(act_tcam, FBNIC_RPC_TCAM_ACT_NUM_ENTRIES);
+};
+
+struct fbnic_act_tcam {
+	struct {
+		u16 tcam[FBNIC_RPC_TCAM_ACT_WORD_LEN];
+	} mask, value;
+	unsigned char state;
+	u16 rss_en_mask;
+	u32 dest;
+};
+
+enum {
+	FBNIC_RSS_EN_HOST_UDP6,
+	FBNIC_RSS_EN_HOST_UDP4,
+	FBNIC_RSS_EN_HOST_TCP6,
+	FBNIC_RSS_EN_HOST_TCP4,
+	FBNIC_RSS_EN_HOST_IP6,
+	FBNIC_RSS_EN_HOST_IP4,
+	FBNIC_RSS_EN_HOST_ETHER,
+	FBNIC_RSS_EN_XCAST_UDP6,
+#define FBNIC_RSS_EN_NUM_UNICAST FBNIC_RSS_EN_XCAST_UDP6
+	FBNIC_RSS_EN_XCAST_UDP4,
+	FBNIC_RSS_EN_XCAST_TCP6,
+	FBNIC_RSS_EN_XCAST_TCP4,
+	FBNIC_RSS_EN_XCAST_IP6,
+	FBNIC_RSS_EN_XCAST_IP4,
+	FBNIC_RSS_EN_XCAST_ETHER,
+	FBNIC_RSS_EN_NUM_ENTRIES
+};
+
+/* Reserve the first 2 entries for the use by the BMC so that we can
+ * avoid allowing rules to get in the way of BMC unicast traffic.
+ */
+#define FBNIC_RPC_ACT_TBL_BMC_OFFSET		0
+#define FBNIC_RPC_ACT_TBL_BMC_ALL_MULTI_OFFSET	1
+
+/* This should leave us with 48 total entries in the TCAM that can be used
+ * for NFC after also deducting the 14 needed for RSS table programming.
+ */
+#define FBNIC_RPC_ACT_TBL_NFC_OFFSET		2
+
+/* We reserve the last 14 entries for RSS rules on the host. The BMC
+ * unicast rule will need to be populated above these and is expected to
+ * use MACDA TCAM entry 23 to store the BMC MAC address.
+ */
+#define FBNIC_RPC_ACT_TBL_RSS_OFFSET \
+	(FBNIC_RPC_ACT_TBL_NUM_ENTRIES - FBNIC_RSS_EN_NUM_ENTRIES)
+
+#define FBNIC_RPC_ACT_TBL_NFC_ENTRIES \
+	(FBNIC_RPC_ACT_TBL_RSS_OFFSET - FBNIC_RPC_ACT_TBL_NFC_OFFSET)
+
+/* Flags used to identify the owner for this MAC filter. Note that any
+ * flags set for Broadcast thru Promisc indicate that the rule belongs
+ * to the RSS filters for the host.
+ */
+enum {
+	FBNIC_MAC_ADDR_T_BMC            = 0,
+	FBNIC_MAC_ADDR_T_BROADCAST	= FBNIC_RPC_ACT_TBL_RSS_OFFSET,
+#define FBNIC_MAC_ADDR_T_HOST_START	FBNIC_MAC_ADDR_T_BROADCAST
+	FBNIC_MAC_ADDR_T_MULTICAST,
+	FBNIC_MAC_ADDR_T_UNICAST,
+	FBNIC_MAC_ADDR_T_ALLMULTI,	/* BROADCAST ... MULTICAST*/
+	FBNIC_MAC_ADDR_T_PROMISC,	/* BROADCAST ... UNICAST */
+	FBNIC_MAC_ADDR_T_HOST_LAST
+};
+
+#define FBNIC_MAC_ADDR_T_HOST_LEN \
+	(FBNIC_MAC_ADDR_T_HOST_LAST - FBNIC_MAC_ADDR_T_HOST_START)
+
+#define FBNIC_RPC_TCAM_ACT0_IPSRC_IDX		CSR_GENMASK(2, 0)
+#define FBNIC_RPC_TCAM_ACT0_IPSRC_VALID		CSR_BIT(3)
+#define FBNIC_RPC_TCAM_ACT0_IPDST_IDX		CSR_GENMASK(6, 4)
+#define FBNIC_RPC_TCAM_ACT0_IPDST_VALID		CSR_BIT(7)
+#define FBNIC_RPC_TCAM_ACT0_OUTER_IPSRC_IDX	CSR_GENMASK(10, 8)
+#define FBNIC_RPC_TCAM_ACT0_OUTER_IPSRC_VALID	CSR_BIT(11)
+#define FBNIC_RPC_TCAM_ACT0_OUTER_IPDST_IDX	CSR_GENMASK(14, 12)
+#define FBNIC_RPC_TCAM_ACT0_OUTER_IPDST_VALID	CSR_BIT(15)
+
+#define FBNIC_RPC_TCAM_ACT1_L2_MACDA_IDX	CSR_GENMASK(9, 5)
+#define FBNIC_RPC_TCAM_ACT1_L2_MACDA_VALID	CSR_BIT(10)
+#define FBNIC_RPC_TCAM_ACT1_IP_IS_V6		CSR_BIT(11)
+#define FBNIC_RPC_TCAM_ACT1_IP_VALID		CSR_BIT(12)
+#define FBNIC_RPC_TCAM_ACT1_OUTER_IP_VALID	CSR_BIT(13)
+#define FBNIC_RPC_TCAM_ACT1_L4_IS_UDP		CSR_BIT(14)
+#define FBNIC_RPC_TCAM_ACT1_L4_VALID		CSR_BIT(15)
+
+/* TCAM 0 - 3 reserved for BMC MAC addresses */
+#define FBNIC_RPC_TCAM_MACDA_BMC_ADDR_IDX	0
+/* TCAM 4 reserved for broadcast MAC address */
+#define FBNIC_RPC_TCAM_MACDA_BROADCAST_IDX	4
+/* TCAMs 5 - 30 will be used for multicast and unicast addresses. The
+ * boundary between the two can be variable it is currently set to 24
+ * on which the unicast addresses start. The general idea is that we will
+ * always go top-down with unicast, and bottom-up with multicast so that
+ * there should be free-space in the middle between the two.
+ *
+ * The entry at MADCA_DEFAULT_BOUNDARY is a special case as it can be used
+ * for the ALL MULTI address if the list is full, or the BMC has requested
+ * it.
+ */
+#define FBNIC_RPC_TCAM_MACDA_MULTICAST_IDX	5
+#define FBNIC_RPC_TCAM_MACDA_DEFAULT_BOUNDARY	24
+#define FBNIC_RPC_TCAM_MACDA_HOST_ADDR_IDX	30
+/* Reserved for use to record Multicast promisc, or Promiscuous */
+#define FBNIC_RPC_TCAM_MACDA_PROMISC_IDX	31
+
+enum {
+	FBNIC_UDP6_HASH_OPT,
+	FBNIC_UDP4_HASH_OPT,
+	FBNIC_TCP6_HASH_OPT,
+	FBNIC_TCP4_HASH_OPT,
+#define FBNIC_L4_HASH_OPT FBNIC_TCP4_HASH_OPT
+	FBNIC_IPV6_HASH_OPT,
+	FBNIC_IPV4_HASH_OPT,
+#define FBNIC_IP_HASH_OPT FBNIC_IPV4_HASH_OPT
+	FBNIC_ETHER_HASH_OPT,
+	FBNIC_NUM_HASH_OPT,
+};
+
+struct fbnic_dev;
+struct fbnic_net;
+
+void fbnic_bmc_rpc_init(struct fbnic_dev *fbd);
+void fbnic_bmc_rpc_all_multi_config(struct fbnic_dev *fbd, bool enable_host);
+void fbnic_bmc_rpc_check(struct fbnic_dev *fbd);
+
+void fbnic_reset_indir_tbl(struct fbnic_net *fbn);
+void fbnic_rss_key_fill(u32 *buffer);
+void fbnic_rss_init_en_mask(struct fbnic_net *fbn);
+void fbnic_rss_disable_hw(struct fbnic_dev *fbd);
+void fbnic_rss_reinit_hw(struct fbnic_dev *fbd, struct fbnic_net *fbn);
+void fbnic_rss_reinit(struct fbnic_dev *fbd, struct fbnic_net *fbn);
+u16 fbnic_flow_hash_2_rss_en_mask(struct fbnic_net *fbn, int flow_type);
+
+int __fbnic_xc_unsync(struct fbnic_mac_addr *mac_addr, unsigned int tcam_idx);
+struct fbnic_mac_addr *__fbnic_uc_sync(struct fbnic_dev *fbd,
+				       const unsigned char *addr);
+struct fbnic_mac_addr *__fbnic_mc_sync(struct fbnic_dev *fbd,
+				       const unsigned char *addr);
+void fbnic_sift_macda(struct fbnic_dev *fbd);
+void fbnic_write_macda(struct fbnic_dev *fbd);
+
+void fbnic_promisc_sync(struct fbnic_dev *fbd,
+			bool uc_promisc, bool mc_promisc);
+
+struct fbnic_ip_addr *__fbnic_ip4_sync(struct fbnic_dev *fbd,
+				       struct fbnic_ip_addr *ip_addr,
+				       const struct in_addr *addr,
+				       const struct in_addr *mask);
+struct fbnic_ip_addr *__fbnic_ip6_sync(struct fbnic_dev *fbd,
+				       struct fbnic_ip_addr *ip_addr,
+				       const struct in6_addr *addr,
+				       const struct in6_addr *mask);
+int __fbnic_ip_unsync(struct fbnic_ip_addr *ip_addr, unsigned int tcam_idx);
+void fbnic_write_ip_addr(struct fbnic_dev *fbd);
+
+static inline int __fbnic_uc_unsync(struct fbnic_mac_addr *mac_addr)
+{
+	return __fbnic_xc_unsync(mac_addr, FBNIC_MAC_ADDR_T_UNICAST);
+}
+
+static inline int __fbnic_mc_unsync(struct fbnic_mac_addr *mac_addr)
+{
+	return __fbnic_xc_unsync(mac_addr, FBNIC_MAC_ADDR_T_MULTICAST);
+}
+
+void fbnic_clear_rules(struct fbnic_dev *fbd);
+void fbnic_write_rules(struct fbnic_dev *fbd);
+void fbnic_write_tce_tcam(struct fbnic_dev *fbd);
+#endif /* _FBNIC_RPC_H_ */

linux-7.2.3/drivers/net/ethernet/meta/fbnic/fbnic_time.c

@@ -0,0 +1,303 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) Meta Platforms, Inc. and affiliates. */
+
+#include <linux/bitfield.h>
+#include <linux/jiffies.h>
+#include <linux/limits.h>
+#include <linux/ptp_clock_kernel.h>
+#include <linux/timer.h>
+
+#include "fbnic.h"
+#include "fbnic_csr.h"
+#include "fbnic_netdev.h"
+
+/* FBNIC timing & PTP implementation
+ * Datapath uses truncated 40b timestamps for scheduling and event reporting.
+ * We need to promote those to full 64b, hence we periodically cache the top
+ * 32bit of the HW time counter. Since this makes our time reporting non-atomic
+ * we leave the HW clock free running and adjust time offsets in SW as needed.
+ * Time offset is 64bit - we need a seq counter for 32bit machines.
+ * Time offset and the cache of top bits are independent so we don't need
+ * a coherent snapshot of both - READ_ONCE()/WRITE_ONCE() + writer side lock
+ * are enough.
+ */
+
+/* Period of refresh of top bits of timestamp, give ourselves a 8x margin.
+ * This should translate to once a minute.
+ * The use of nsecs_to_jiffies() should be safe for a <=40b nsec value.
+ */
+#define FBNIC_TS_HIGH_REFRESH_JIF	nsecs_to_jiffies((1ULL << 40) / 16)
+
+static struct fbnic_dev *fbnic_from_ptp_info(struct ptp_clock_info *ptp)
+{
+	return container_of(ptp, struct fbnic_dev, ptp_info);
+}
+
+/* This function is "slow" because we could try guessing which high part
+ * is correct based on low instead of re-reading, and skip reading @hi
+ * twice altogether if @lo is far enough from 0.
+ */
+static u64 __fbnic_time_get_slow(struct fbnic_dev *fbd)
+{
+	u32 hi, lo;
+
+	lockdep_assert_held(&fbd->time_lock);
+
+	do {
+		hi = fbnic_rd32(fbd, FBNIC_PTP_CTR_VAL_HI);
+		lo = fbnic_rd32(fbd, FBNIC_PTP_CTR_VAL_LO);
+	} while (hi != fbnic_rd32(fbd, FBNIC_PTP_CTR_VAL_HI));
+
+	return (u64)hi << 32 | lo;
+}
+
+static void __fbnic_time_set_addend(struct fbnic_dev *fbd, u64 addend)
+{
+	lockdep_assert_held(&fbd->time_lock);
+
+	fbnic_wr32(fbd, FBNIC_PTP_ADD_VAL_NS,
+		   FIELD_PREP(FBNIC_PTP_ADD_VAL_NS_MASK, addend >> 32));
+	fbnic_wr32(fbd, FBNIC_PTP_ADD_VAL_SUBNS, (u32)addend);
+}
+
+static void fbnic_ptp_fresh_check(struct fbnic_dev *fbd)
+{
+	if (time_is_after_jiffies(fbd->last_read +
+				  FBNIC_TS_HIGH_REFRESH_JIF * 3 / 2))
+		return;
+
+	dev_warn(fbd->dev, "NIC timestamp refresh stall, delayed by %lu sec\n",
+		 (jiffies - fbd->last_read - FBNIC_TS_HIGH_REFRESH_JIF) / HZ);
+}
+
+static void fbnic_ptp_refresh_time(struct fbnic_dev *fbd, struct fbnic_net *fbn)
+{
+	unsigned long flags;
+	u32 hi;
+
+	spin_lock_irqsave(&fbd->time_lock, flags);
+	hi = fbnic_rd32(fbn->fbd, FBNIC_PTP_CTR_VAL_HI);
+	if (!fbnic_present(fbd))
+		goto out; /* Don't bother handling, reset is pending */
+	/* Let's keep high cached value a bit lower to avoid race with
+	 * incoming timestamps. The logic in fbnic_ts40_to_ns() will
+	 * take care of overflow in this case. It will make cached time
+	 * ~1 minute lower and incoming timestamp will always be later
+	 * then cached time.
+	 */
+	WRITE_ONCE(fbn->time_high, hi - 16);
+	fbd->last_read = jiffies;
+ out:
+	spin_unlock_irqrestore(&fbd->time_lock, flags);
+}
+
+static long fbnic_ptp_do_aux_work(struct ptp_clock_info *ptp)
+{
+	struct fbnic_dev *fbd = fbnic_from_ptp_info(ptp);
+	struct fbnic_net *fbn;
+
+	fbn = netdev_priv(fbd->netdev);
+
+	fbnic_ptp_fresh_check(fbd);
+	fbnic_ptp_refresh_time(fbd, fbn);
+
+	return FBNIC_TS_HIGH_REFRESH_JIF;
+}
+
+static int fbnic_ptp_adjfine(struct ptp_clock_info *ptp, long scaled_ppm)
+{
+	struct fbnic_dev *fbd = fbnic_from_ptp_info(ptp);
+	u64 addend, dclk_period;
+	unsigned long flags;
+
+	/* d_clock is 600 MHz; which in Q16.32 fixed point ns is: */
+	dclk_period = (((u64)1000000000) << 32) / FBNIC_CLOCK_FREQ;
+	addend = adjust_by_scaled_ppm(dclk_period, scaled_ppm);
+
+	spin_lock_irqsave(&fbd->time_lock, flags);
+	__fbnic_time_set_addend(fbd, addend);
+	fbnic_wr32(fbd, FBNIC_PTP_ADJUST, FBNIC_PTP_ADJUST_ADDEND_SET);
+
+	/* Flush, make sure FBNIC_PTP_ADD_VAL_* is stable for at least 4 clks */
+	fbnic_rd32(fbd, FBNIC_PTP_SPARE);
+	spin_unlock_irqrestore(&fbd->time_lock, flags);
+
+	return fbnic_present(fbd) ? 0 : -EIO;
+}
+
+static int fbnic_ptp_adjtime(struct ptp_clock_info *ptp, s64 delta)
+{
+	struct fbnic_dev *fbd = fbnic_from_ptp_info(ptp);
+	struct fbnic_net *fbn;
+	unsigned long flags;
+
+	fbn = netdev_priv(fbd->netdev);
+
+	spin_lock_irqsave(&fbd->time_lock, flags);
+	u64_stats_update_begin(&fbn->time_seq);
+	WRITE_ONCE(fbn->time_offset, READ_ONCE(fbn->time_offset) + delta);
+	u64_stats_update_end(&fbn->time_seq);
+	spin_unlock_irqrestore(&fbd->time_lock, flags);
+
+	return 0;
+}
+
+static int
+fbnic_ptp_gettimex64(struct ptp_clock_info *ptp, struct timespec64 *ts,
+		     struct ptp_system_timestamp *sts)
+{
+	struct fbnic_dev *fbd = fbnic_from_ptp_info(ptp);
+	struct fbnic_net *fbn;
+	unsigned long flags;
+	u64 time_ns;
+	u32 hi, lo;
+
+	fbn = netdev_priv(fbd->netdev);
+
+	spin_lock_irqsave(&fbd->time_lock, flags);
+
+	do {
+		hi = fbnic_rd32(fbd, FBNIC_PTP_CTR_VAL_HI);
+		ptp_read_system_prets(sts);
+		lo = fbnic_rd32(fbd, FBNIC_PTP_CTR_VAL_LO);
+		ptp_read_system_postts(sts);
+		/* Similarly to comment above __fbnic_time_get_slow()
+		 * - this can be optimized if needed.
+		 */
+	} while (hi != fbnic_rd32(fbd, FBNIC_PTP_CTR_VAL_HI));
+
+	time_ns = ((u64)hi << 32 | lo) + fbn->time_offset;
+	spin_unlock_irqrestore(&fbd->time_lock, flags);
+
+	if (!fbnic_present(fbd))
+		return -EIO;
+
+	*ts = ns_to_timespec64(time_ns);
+
+	return 0;
+}
+
+static int
+fbnic_ptp_settime64(struct ptp_clock_info *ptp, const struct timespec64 *ts)
+{
+	struct fbnic_dev *fbd = fbnic_from_ptp_info(ptp);
+	struct fbnic_net *fbn;
+	unsigned long flags;
+	u64 dev_ns, host_ns;
+	int ret;
+
+	fbn = netdev_priv(fbd->netdev);
+
+	host_ns = timespec64_to_ns(ts);
+
+	spin_lock_irqsave(&fbd->time_lock, flags);
+
+	dev_ns = __fbnic_time_get_slow(fbd);
+
+	if (fbnic_present(fbd)) {
+		u64_stats_update_begin(&fbn->time_seq);
+		WRITE_ONCE(fbn->time_offset, host_ns - dev_ns);
+		u64_stats_update_end(&fbn->time_seq);
+		ret = 0;
+	} else {
+		ret = -EIO;
+	}
+	spin_unlock_irqrestore(&fbd->time_lock, flags);
+
+	return ret;
+}
+
+static const struct ptp_clock_info fbnic_ptp_info = {
+	.owner			= THIS_MODULE,
+	/* 1,000,000,000 - 1 PPB to ensure increment is positive
+	 * after max negative adjustment.
+	 */
+	.max_adj		= 999999999,
+	.do_aux_work		= fbnic_ptp_do_aux_work,
+	.adjfine		= fbnic_ptp_adjfine,
+	.adjtime		= fbnic_ptp_adjtime,
+	.gettimex64		= fbnic_ptp_gettimex64,
+	.settime64		= fbnic_ptp_settime64,
+};
+
+static void fbnic_ptp_reset(struct fbnic_dev *fbd)
+{
+	struct fbnic_net *fbn = netdev_priv(fbd->netdev);
+	u64 dclk_period;
+
+	fbnic_wr32(fbd, FBNIC_PTP_CTRL,
+		   FBNIC_PTP_CTRL_EN |
+		   FIELD_PREP(FBNIC_PTP_CTRL_TICK_IVAL, 1));
+
+	/* d_clock is 600 MHz; which in Q16.32 fixed point ns is: */
+	dclk_period = (((u64)1000000000) << 32) / FBNIC_CLOCK_FREQ;
+
+	__fbnic_time_set_addend(fbd, dclk_period);
+
+	fbnic_wr32(fbd, FBNIC_PTP_INIT_HI, 0);
+	fbnic_wr32(fbd, FBNIC_PTP_INIT_LO, 0);
+
+	fbnic_wr32(fbd, FBNIC_PTP_ADJUST, FBNIC_PTP_ADJUST_INIT);
+
+	fbnic_wr32(fbd, FBNIC_PTP_CTRL,
+		   FBNIC_PTP_CTRL_EN |
+		   FBNIC_PTP_CTRL_TQS_OUT_EN |
+		   FIELD_PREP(FBNIC_PTP_CTRL_MAC_OUT_IVAL, 3) |
+		   FIELD_PREP(FBNIC_PTP_CTRL_TICK_IVAL, 1));
+
+	fbnic_rd32(fbd, FBNIC_PTP_SPARE);
+
+	fbn->time_offset = 0;
+	fbn->time_high = 0;
+}
+
+void fbnic_time_init(struct fbnic_net *fbn)
+{
+	/* This is not really a statistic, but the locking primitive fits
+	 * our usecase perfectly, we need an atomic 8 bytes READ_ONCE() /
+	 * WRITE_ONCE() behavior.
+	 */
+	u64_stats_init(&fbn->time_seq);
+}
+
+int fbnic_time_start(struct fbnic_net *fbn)
+{
+	fbnic_ptp_refresh_time(fbn->fbd, fbn);
+	/* Assume that fbnic_ptp_do_aux_work() will never be called if not
+	 * scheduled here
+	 */
+	return ptp_schedule_worker(fbn->fbd->ptp, FBNIC_TS_HIGH_REFRESH_JIF);
+}
+
+void fbnic_time_stop(struct fbnic_net *fbn)
+{
+	ptp_cancel_worker_sync(fbn->fbd->ptp);
+	fbnic_ptp_fresh_check(fbn->fbd);
+}
+
+int fbnic_ptp_setup(struct fbnic_dev *fbd)
+{
+	struct device *dev = fbd->dev;
+	unsigned long flags;
+
+	spin_lock_init(&fbd->time_lock);
+
+	spin_lock_irqsave(&fbd->time_lock, flags); /* Appease lockdep */
+	fbnic_ptp_reset(fbd);
+	spin_unlock_irqrestore(&fbd->time_lock, flags);
+
+	memcpy(&fbd->ptp_info, &fbnic_ptp_info, sizeof(fbnic_ptp_info));
+
+	fbd->ptp = ptp_clock_register(&fbd->ptp_info, dev);
+	if (IS_ERR(fbd->ptp))
+		dev_err(dev, "Failed to register PTP: %pe\n", fbd->ptp);
+
+	return PTR_ERR_OR_ZERO(fbd->ptp);
+}
+
+void fbnic_ptp_destroy(struct fbnic_dev *fbd)
+{
+	if (!fbd->ptp)
+		return;
+	ptp_clock_unregister(fbd->ptp);
+}

linux-7.2.3/drivers/net/ethernet/meta/fbnic/fbnic_tlv.c

@@ -0,0 +1,836 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) Meta Platforms, Inc. and affiliates. */
+
+#include <linux/gfp.h>
+#include <linux/mm.h>
+#include <linux/once.h>
+#include <linux/random.h>
+#include <linux/string.h>
+#include <uapi/linux/if_ether.h>
+
+#include "fbnic_tlv.h"
+
+/**
+ * fbnic_tlv_msg_alloc - Allocate page and initialize FW message header
+ * @msg_id: Identifier for new message we are starting
+ *
+ * Return: pointer to start of message, or NULL on failure.
+ *
+ * Allocates a page and initializes message header at start of page.
+ * Initial message size is 1 DWORD which is just the header.
+ **/
+struct fbnic_tlv_msg *fbnic_tlv_msg_alloc(u16 msg_id)
+{
+	struct fbnic_tlv_hdr hdr = { 0 };
+	struct fbnic_tlv_msg *msg;
+
+	msg = (struct fbnic_tlv_msg *)__get_free_page(GFP_KERNEL);
+	if (!msg)
+		return NULL;
+
+	/* Start with zero filled header and then back fill with data */
+	hdr.type = msg_id;
+	hdr.is_msg = 1;
+	hdr.len = cpu_to_le16(1);
+
+	/* Copy header into start of message */
+	msg->hdr = hdr;
+
+	return msg;
+}
+
+/**
+ * fbnic_tlv_attr_put_flag - Add flag value to message
+ * @msg: Message header we are adding flag attribute to
+ * @attr_id: ID of flag attribute we are adding to message
+ *
+ * Return: -ENOSPC if there is no room for the attribute. Otherwise 0.
+ *
+ * Adds a 1 DWORD flag attribute to the message. The presence of this
+ * attribute can be used as a boolean value indicating true, otherwise the
+ * value is considered false.
+ **/
+int fbnic_tlv_attr_put_flag(struct fbnic_tlv_msg *msg, const u16 attr_id)
+{
+	int attr_max_len = PAGE_SIZE - offset_in_page(msg) - sizeof(*msg);
+	struct fbnic_tlv_hdr hdr = { 0 };
+	struct fbnic_tlv_msg *attr;
+
+	attr_max_len -= le16_to_cpu(msg->hdr.len) * sizeof(u32);
+	if (attr_max_len < sizeof(*attr))
+		return -ENOSPC;
+
+	/* Get header pointer and bump attr to start of data */
+	attr = &msg[le16_to_cpu(msg->hdr.len)];
+
+	/* Record attribute type and size */
+	hdr.type = attr_id;
+	hdr.len = cpu_to_le16(sizeof(hdr));
+
+	attr->hdr = hdr;
+	le16_add_cpu(&msg->hdr.len,
+		     FBNIC_TLV_MSG_SIZE(le16_to_cpu(hdr.len)));
+
+	return 0;
+}
+
+/**
+ * fbnic_tlv_attr_put_value - Add data to message
+ * @msg: Message header we are adding flag attribute to
+ * @attr_id: ID of flag attribute we are adding to message
+ * @value: Pointer to data to be stored
+ * @len: Size of data to be stored.
+ *
+ * Return: -ENOSPC if there is no room for the attribute. Otherwise 0.
+ *
+ * Adds header and copies data pointed to by value into the message. The
+ * result is rounded up to the nearest DWORD for sizing so that the
+ * headers remain aligned.
+ *
+ * The assumption is that the value field is in a format where byte
+ * ordering can be guaranteed such as a byte array or a little endian
+ * format.
+ **/
+int fbnic_tlv_attr_put_value(struct fbnic_tlv_msg *msg, const u16 attr_id,
+			     const void *value, const int len)
+{
+	int attr_max_len = PAGE_SIZE - offset_in_page(msg) - sizeof(*msg);
+	struct fbnic_tlv_hdr hdr = { 0 };
+	struct fbnic_tlv_msg *attr;
+
+	attr_max_len -= le16_to_cpu(msg->hdr.len) * sizeof(u32);
+	if (attr_max_len < sizeof(*attr) + len)
+		return -ENOSPC;
+
+	/* Get header pointer and bump attr to start of data */
+	attr = &msg[le16_to_cpu(msg->hdr.len)];
+
+	/* Record attribute type and size */
+	hdr.type = attr_id;
+	hdr.len = cpu_to_le16(sizeof(hdr) + len);
+
+	/* Zero pad end of region to be written if we aren't aligned */
+	if (len % sizeof(hdr))
+		attr->value[len / sizeof(hdr)] = 0;
+
+	/* Copy data over */
+	memcpy(attr->value, value, len);
+
+	attr->hdr = hdr;
+	le16_add_cpu(&msg->hdr.len,
+		     FBNIC_TLV_MSG_SIZE(le16_to_cpu(hdr.len)));
+
+	return 0;
+}
+
+/**
+ * __fbnic_tlv_attr_put_int - Add integer to message
+ * @msg: Message header we are adding flag attribute to
+ * @attr_id: ID of flag attribute we are adding to message
+ * @value: Data to be stored
+ * @len: Size of data to be stored, either 4 or 8 bytes.
+ *
+ * Return: -ENOSPC if there is no room for the attribute. Otherwise 0.
+ *
+ * Adds header and copies data pointed to by value into the message. Will
+ * format the data as little endian.
+ **/
+int __fbnic_tlv_attr_put_int(struct fbnic_tlv_msg *msg, const u16 attr_id,
+			     s64 value, const int len)
+{
+	__le64 le64_value = cpu_to_le64(value);
+
+	return fbnic_tlv_attr_put_value(msg, attr_id, &le64_value, len);
+}
+
+/**
+ * fbnic_tlv_attr_put_mac_addr - Add mac_addr to message
+ * @msg: Message header we are adding flag attribute to
+ * @attr_id: ID of flag attribute we are adding to message
+ * @mac_addr: Byte pointer to MAC address to be stored
+ *
+ * Return: -ENOSPC if there is no room for the attribute. Otherwise 0.
+ *
+ * Adds header and copies data pointed to by mac_addr into the message. Will
+ * copy the address raw so it will be in big endian with start of MAC
+ * address at start of attribute.
+ **/
+int fbnic_tlv_attr_put_mac_addr(struct fbnic_tlv_msg *msg, const u16 attr_id,
+				const u8 *mac_addr)
+{
+	return fbnic_tlv_attr_put_value(msg, attr_id, mac_addr, ETH_ALEN);
+}
+
+/**
+ * fbnic_tlv_attr_put_string - Add string to message
+ * @msg: Message header we are adding flag attribute to
+ * @attr_id: ID of flag attribute we are adding to message
+ * @string: Byte pointer to null terminated string to be stored
+ *
+ * Return: -ENOSPC if there is no room for the attribute. Otherwise 0.
+ *
+ * Adds header and copies data pointed to by string into the message. Will
+ * copy the address raw so it will be in byte order.
+ **/
+int fbnic_tlv_attr_put_string(struct fbnic_tlv_msg *msg, u16 attr_id,
+			      const char *string)
+{
+	int attr_max_len = PAGE_SIZE - sizeof(*msg);
+	int str_len = 1;
+
+	/* The max length will be message minus existing message and new
+	 * attribute header. Since the message is measured in DWORDs we have
+	 * to multiply the size by 4.
+	 *
+	 * The string length doesn't include the \0 so we have to add one to
+	 * the final value, so start with that as our initial value.
+	 *
+	 * We will verify if the string will fit in fbnic_tlv_attr_put_value()
+	 */
+	attr_max_len -= le16_to_cpu(msg->hdr.len) * sizeof(u32);
+	str_len += strnlen(string, attr_max_len);
+
+	return fbnic_tlv_attr_put_value(msg, attr_id, string, str_len);
+}
+
+/**
+ * fbnic_tlv_attr_get_unsigned - Retrieve unsigned value from result
+ * @attr: Attribute to retrieve data from
+ * @def: The default value if attr is NULL
+ *
+ * Return: unsigned 64b value containing integer value
+ **/
+u64 fbnic_tlv_attr_get_unsigned(struct fbnic_tlv_msg *attr, u64 def)
+{
+	__le64 le64_value = 0;
+
+	if (!attr)
+		return def;
+
+	memcpy(&le64_value, &attr->value[0],
+	       le16_to_cpu(attr->hdr.len) - sizeof(*attr));
+
+	return le64_to_cpu(le64_value);
+}
+
+/**
+ * fbnic_tlv_attr_get_signed - Retrieve signed value from result
+ * @attr: Attribute to retrieve data from
+ * @def: The default value if attr is NULL
+ *
+ * Return: signed 64b value containing integer value
+ **/
+s64 fbnic_tlv_attr_get_signed(struct fbnic_tlv_msg *attr, s64 def)
+{
+	__le64 le64_value = 0;
+	int shift;
+	s64 value;
+
+	if (!attr)
+		return def;
+
+	shift = (8 + sizeof(*attr) - le16_to_cpu(attr->hdr.len)) * 8;
+
+	/* Copy the value and adjust for byte ordering */
+	memcpy(&le64_value, &attr->value[0],
+	       le16_to_cpu(attr->hdr.len) - sizeof(*attr));
+	value = le64_to_cpu(le64_value);
+
+	/* Sign extend the return value by using a pair of shifts */
+	return (value << shift) >> shift;
+}
+
+/**
+ * fbnic_tlv_attr_get_string - Retrieve string value from result
+ * @attr: Attribute to retrieve data from
+ * @dst: Pointer to an allocated string to store the data
+ * @dstsize: The maximum size which can be in dst
+ *
+ * Return: the size of the string read from firmware or negative error.
+ **/
+ssize_t fbnic_tlv_attr_get_string(struct fbnic_tlv_msg *attr, char *dst,
+				  size_t dstsize)
+{
+	size_t srclen, len;
+	ssize_t ret;
+
+	if (!attr)
+		return -EINVAL;
+
+	if (dstsize == 0)
+		return -E2BIG;
+
+	srclen = le16_to_cpu(attr->hdr.len) - sizeof(*attr);
+	if (srclen > 0 && ((char *)attr->value)[srclen - 1] == '\0')
+		srclen--;
+
+	if (srclen >= dstsize) {
+		len = dstsize - 1;
+		ret = -E2BIG;
+	} else {
+		len = srclen;
+		ret = len;
+	}
+
+	memcpy(dst, &attr->value, len);
+	/* Zero pad end of dst. */
+	memset(dst + len, 0, dstsize - len);
+
+	return ret;
+}
+
+/**
+ * fbnic_tlv_attr_nest_start - Add nested attribute header to message
+ * @msg: Message header we are adding flag attribute to
+ * @attr_id: ID of flag attribute we are adding to message
+ *
+ * Return: NULL if there is no room for the attribute. Otherwise a pointer
+ * to the new attribute header.
+ *
+ * New header length is stored initially in DWORDs.
+ **/
+struct fbnic_tlv_msg *fbnic_tlv_attr_nest_start(struct fbnic_tlv_msg *msg,
+						u16 attr_id)
+{
+	int attr_max_len = PAGE_SIZE - offset_in_page(msg) - sizeof(*msg);
+	struct fbnic_tlv_msg *attr = &msg[le16_to_cpu(msg->hdr.len)];
+	struct fbnic_tlv_hdr hdr = { 0 };
+
+	/* Make sure we have space for at least the nest header plus one more */
+	attr_max_len -= le16_to_cpu(msg->hdr.len) * sizeof(u32);
+	if (attr_max_len < sizeof(*attr) * 2)
+		return NULL;
+
+	/* Record attribute type and size */
+	hdr.type = attr_id;
+
+	/* Add current message length to account for consumption within the
+	 * page and leave it as a multiple of DWORDs, we will shift to
+	 * bytes when we close it out.
+	 */
+	hdr.len = cpu_to_le16(1);
+
+	attr->hdr = hdr;
+
+	return attr;
+}
+
+/**
+ * fbnic_tlv_attr_nest_stop - Close out nested attribute and add it to message
+ * @msg: Message header we are adding flag attribute to
+ *
+ * Closes out nested attribute, adds length to message, and then bumps
+ * length from DWORDs to bytes to match other attributes.
+ **/
+void fbnic_tlv_attr_nest_stop(struct fbnic_tlv_msg *msg)
+{
+	struct fbnic_tlv_msg *attr = &msg[le16_to_cpu(msg->hdr.len)];
+	u16 len = le16_to_cpu(attr->hdr.len);
+
+	/* Add attribute to message if there is more than just a header */
+	if (len <= 1)
+		return;
+
+	le16_add_cpu(&msg->hdr.len, len);
+
+	/* Convert from DWORDs to bytes */
+	attr->hdr.len = cpu_to_le16(len * sizeof(u32));
+}
+
+static int
+fbnic_tlv_attr_validate(struct fbnic_tlv_msg *attr,
+			const struct fbnic_tlv_index *tlv_index)
+{
+	u16 len = le16_to_cpu(attr->hdr.len) - sizeof(*attr);
+	u16 attr_id = attr->hdr.type;
+	__le32 *value = &attr->value[0];
+
+	if (attr->hdr.is_msg)
+		return -EINVAL;
+
+	if (attr_id >= FBNIC_TLV_RESULTS_MAX)
+		return -EINVAL;
+
+	while (tlv_index->id != attr_id) {
+		if  (tlv_index->id == FBNIC_TLV_ATTR_ID_UNKNOWN) {
+			if (attr->hdr.cannot_ignore)
+				return -ENOENT;
+			return le16_to_cpu(attr->hdr.len);
+		}
+
+		tlv_index++;
+	}
+
+	if (offset_in_page(attr) + len > PAGE_SIZE - sizeof(*attr))
+		return -E2BIG;
+
+	switch (tlv_index->type) {
+	case FBNIC_TLV_STRING:
+		if (!len || len > tlv_index->len)
+			return -EINVAL;
+		if (((char *)value)[len - 1])
+			return -EINVAL;
+		break;
+	case FBNIC_TLV_FLAG:
+		if (len)
+			return -EINVAL;
+		break;
+	case FBNIC_TLV_UNSIGNED:
+	case FBNIC_TLV_SIGNED:
+		if (tlv_index->len > sizeof(__le64))
+			return -EINVAL;
+		fallthrough;
+	case FBNIC_TLV_BINARY:
+		if (!len || len > tlv_index->len)
+			return -EINVAL;
+		break;
+	case FBNIC_TLV_NESTED:
+	case FBNIC_TLV_ARRAY:
+		if (len % 4)
+			return -EINVAL;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+/**
+ * fbnic_tlv_attr_parse_array - Parse array of attributes into results array
+ * @attr: Start of attributes in the message
+ * @len: Length of attributes in the message
+ * @results: Array of pointers to store the results of parsing
+ * @tlv_index: List of TLV attributes to be parsed from message
+ * @tlv_attr_id: Specific ID that is repeated in array
+ * @array_len: Number of results to store in results array
+ *
+ * Return: zero on success, or negative value on error.
+ *
+ * Will take a list of attributes and a parser definition and will capture
+ * the results in the results array to have the data extracted later.
+ **/
+int fbnic_tlv_attr_parse_array(struct fbnic_tlv_msg *attr, int len,
+			       struct fbnic_tlv_msg **results,
+			       const struct fbnic_tlv_index *tlv_index,
+			       u16 tlv_attr_id, size_t array_len)
+{
+	int i = 0;
+
+	/* Initialize results table to NULL. */
+	memset(results, 0, array_len * sizeof(results[0]));
+
+	/* Nothing to parse if header was only thing there */
+	if (!len)
+		return 0;
+
+	/* Work through list of attributes, parsing them as necessary */
+	while (len > 0) {
+		u16 attr_id = attr->hdr.type;
+		u16 attr_len;
+		int err;
+
+		if (tlv_attr_id != attr_id)
+			return -EINVAL;
+
+		/* Stop parsing on full error */
+		err = fbnic_tlv_attr_validate(attr, tlv_index);
+		if (err < 0)
+			return err;
+
+		if (i >= array_len)
+			return -ENOSPC;
+
+		results[i++] = attr;
+
+		attr_len = FBNIC_TLV_MSG_SIZE(le16_to_cpu(attr->hdr.len));
+		len -= attr_len;
+		attr += attr_len;
+	}
+
+	return len == 0 ? 0 : -EINVAL;
+}
+
+/**
+ * fbnic_tlv_attr_parse - Parse attributes into a list of attribute results
+ * @attr: Start of attributes in the message
+ * @len: Length of attributes in the message
+ * @results: Array of pointers to store the results of parsing
+ * @tlv_index: List of TLV attributes to be parsed from message
+ *
+ * Return: zero on success, or negative value on error.
+ *
+ * Will take a list of attributes and a parser definition and will capture
+ * the results in the results array to have the data extracted later.
+ **/
+int fbnic_tlv_attr_parse(struct fbnic_tlv_msg *attr, int len,
+			 struct fbnic_tlv_msg **results,
+			 const struct fbnic_tlv_index *tlv_index)
+{
+	/* Initialize results table to NULL. */
+	memset(results, 0, sizeof(results[0]) * FBNIC_TLV_RESULTS_MAX);
+
+	/* Nothing to parse if header was only thing there */
+	if (!len)
+		return 0;
+
+	/* Work through list of attributes, parsing them as necessary */
+	while (len > 0) {
+		int err = fbnic_tlv_attr_validate(attr, tlv_index);
+		u16 attr_id = attr->hdr.type;
+		u16 attr_len;
+
+		/* Stop parsing on full error */
+		if (err < 0)
+			return err;
+
+		/* Ignore results for unsupported values */
+		if (!err) {
+			/* Do not overwrite existing entries */
+			if (results[attr_id])
+				return -EADDRINUSE;
+
+			results[attr_id] = attr;
+		}
+
+		attr_len = FBNIC_TLV_MSG_SIZE(le16_to_cpu(attr->hdr.len));
+		len -= attr_len;
+		attr += attr_len;
+	}
+
+	return len == 0 ? 0 : -EINVAL;
+}
+
+/**
+ * fbnic_tlv_msg_parse - Parse message and process via predetermined functions
+ * @opaque: Value passed to parser function to enable driver access
+ * @msg: Message to be parsed.
+ * @parser: TLV message parser definition.
+ *
+ * Return: zero on success, or negative value on error.
+ *
+ * Will take a message a number of message types via the attribute parsing
+ * definitions and function provided for the parser array.
+ **/
+int fbnic_tlv_msg_parse(void *opaque, struct fbnic_tlv_msg *msg,
+			const struct fbnic_tlv_parser *parser)
+{
+	struct fbnic_tlv_msg *results[FBNIC_TLV_RESULTS_MAX];
+	u16 msg_id = msg->hdr.type;
+	int err;
+
+	if (!msg->hdr.is_msg)
+		return -EINVAL;
+
+	if (le16_to_cpu(msg->hdr.len) > PAGE_SIZE / sizeof(u32))
+		return -E2BIG;
+
+	while (parser->id != msg_id) {
+		if (parser->id == FBNIC_TLV_MSG_ID_UNKNOWN)
+			return -ENOENT;
+		parser++;
+	}
+
+	err = fbnic_tlv_attr_parse(&msg[1], le16_to_cpu(msg->hdr.len) - 1,
+				   results, parser->attr);
+	if (err)
+		return err;
+
+	return parser->func(opaque, results);
+}
+
+/**
+ * fbnic_tlv_parser_error - called if message doesn't match known type
+ * @opaque: (unused)
+ * @results: (unused)
+ *
+ * Return: -EBADMSG to indicate the message is an unsupported type
+ **/
+int fbnic_tlv_parser_error(void *opaque, struct fbnic_tlv_msg **results)
+{
+	return -EBADMSG;
+}
+
+#define FBNIC_TLV_TEST_STRING_LEN	32
+
+struct fbnic_tlv_test {
+	u64	test_u64;
+	s64	test_s64;
+	u32	test_u32;
+	s32	test_s32;
+	u16	test_u16;
+	s16	test_s16;
+	u8	test_mac[ETH_ALEN];
+	u8	test_mac_array[4][ETH_ALEN];
+	u8	test_true;
+	u8	test_false;
+	char	test_string[FBNIC_TLV_TEST_STRING_LEN];
+};
+
+static struct fbnic_tlv_test test_struct;
+
+const struct fbnic_tlv_index fbnic_tlv_test_index[] = {
+	FBNIC_TLV_ATTR_U64(FBNIC_TLV_TEST_MSG_U64),
+	FBNIC_TLV_ATTR_S64(FBNIC_TLV_TEST_MSG_S64),
+	FBNIC_TLV_ATTR_U32(FBNIC_TLV_TEST_MSG_U32),
+	FBNIC_TLV_ATTR_S32(FBNIC_TLV_TEST_MSG_S32),
+	FBNIC_TLV_ATTR_U32(FBNIC_TLV_TEST_MSG_U16),
+	FBNIC_TLV_ATTR_S32(FBNIC_TLV_TEST_MSG_S16),
+	FBNIC_TLV_ATTR_MAC_ADDR(FBNIC_TLV_TEST_MSG_MAC_ADDR),
+	FBNIC_TLV_ATTR_FLAG(FBNIC_TLV_TEST_MSG_FLAG_TRUE),
+	FBNIC_TLV_ATTR_FLAG(FBNIC_TLV_TEST_MSG_FLAG_FALSE),
+	FBNIC_TLV_ATTR_STRING(FBNIC_TLV_TEST_MSG_STRING,
+			      FBNIC_TLV_TEST_STRING_LEN),
+	FBNIC_TLV_ATTR_ARRAY(FBNIC_TLV_TEST_MSG_ARRAY),
+	FBNIC_TLV_ATTR_NESTED(FBNIC_TLV_TEST_MSG_NESTED),
+	FBNIC_TLV_ATTR_LAST
+};
+
+static void fbnic_tlv_test_struct_init(void)
+{
+	int i = FBNIC_TLV_TEST_STRING_LEN - 1;
+
+	/* Populate the struct with random data */
+	get_random_once(&test_struct,
+			offsetof(struct fbnic_tlv_test, test_string) + i);
+
+	/* Force true/false to their expected values */
+	test_struct.test_false = false;
+	test_struct.test_true = true;
+
+	/* Convert test_string to a true ASCII string */
+	test_struct.test_string[i] = '\0';
+	while (i--) {
+		/* Force characters into displayable range */
+		if (test_struct.test_string[i] < 64 ||
+		    test_struct.test_string[i] >= 96) {
+			test_struct.test_string[i] %= 32;
+			test_struct.test_string[i] += 64;
+		}
+	}
+}
+
+static int fbnic_tlv_test_attr_data(struct fbnic_tlv_msg *msg)
+{
+	struct fbnic_tlv_msg *array;
+	int err, i;
+
+	err = fbnic_tlv_attr_put_int(msg, FBNIC_TLV_TEST_MSG_U64,
+				     test_struct.test_u64);
+	if (err)
+		return err;
+
+	err = fbnic_tlv_attr_put_int(msg, FBNIC_TLV_TEST_MSG_S64,
+				     test_struct.test_s64);
+	if (err)
+		return err;
+
+	err = fbnic_tlv_attr_put_int(msg, FBNIC_TLV_TEST_MSG_U32,
+				     test_struct.test_u32);
+	if (err)
+		return err;
+
+	err = fbnic_tlv_attr_put_int(msg, FBNIC_TLV_TEST_MSG_S32,
+				     test_struct.test_s32);
+	if (err)
+		return err;
+
+	err = fbnic_tlv_attr_put_int(msg, FBNIC_TLV_TEST_MSG_U16,
+				     test_struct.test_u16);
+	if (err)
+		return err;
+
+	err = fbnic_tlv_attr_put_int(msg, FBNIC_TLV_TEST_MSG_S16,
+				     test_struct.test_s16);
+	if (err)
+		return err;
+
+	err = fbnic_tlv_attr_put_value(msg, FBNIC_TLV_TEST_MSG_MAC_ADDR,
+				       test_struct.test_mac, ETH_ALEN);
+	if (err)
+		return err;
+
+	/* Start MAC address array */
+	array = fbnic_tlv_attr_nest_start(msg, FBNIC_TLV_TEST_MSG_ARRAY);
+	if (!array)
+		return -ENOSPC;
+
+	for (i = 0; i < 4; i++) {
+		err = fbnic_tlv_attr_put_value(array,
+					       FBNIC_TLV_TEST_MSG_MAC_ADDR,
+					       test_struct.test_mac_array[i],
+					       ETH_ALEN);
+		if (err)
+			return err;
+	}
+
+	/* Close array */
+	fbnic_tlv_attr_nest_stop(msg);
+
+	err = fbnic_tlv_attr_put_flag(msg, FBNIC_TLV_TEST_MSG_FLAG_TRUE);
+	if (err)
+		return err;
+
+	return fbnic_tlv_attr_put_string(msg, FBNIC_TLV_TEST_MSG_STRING,
+					 test_struct.test_string);
+}
+
+/**
+ * fbnic_tlv_test_create - Allocate a test message and fill it w/ data
+ * @fbd: FBNIC device structure
+ *
+ * Return: NULL on failure to allocate or pointer to new TLV test message.
+ **/
+struct fbnic_tlv_msg *fbnic_tlv_test_create(struct fbnic_dev *fbd)
+{
+	struct fbnic_tlv_msg *msg, *nest;
+	int err;
+
+	msg = fbnic_tlv_msg_alloc(FBNIC_TLV_MSG_ID_TEST);
+	if (!msg)
+		return NULL;
+
+	/* Randomize struct data */
+	fbnic_tlv_test_struct_init();
+
+	/* Add first level of data to message */
+	err = fbnic_tlv_test_attr_data(msg);
+	if (err)
+		goto free_message;
+
+	/* Start second level nested */
+	nest = fbnic_tlv_attr_nest_start(msg, FBNIC_TLV_TEST_MSG_NESTED);
+	if (!nest)
+		goto free_message;
+
+	/* Add nested data */
+	err = fbnic_tlv_test_attr_data(nest);
+	if (err)
+		goto free_message;
+
+	/* Close nest and report full message */
+	fbnic_tlv_attr_nest_stop(msg);
+
+	return msg;
+free_message:
+	free_page((unsigned long)msg);
+	return NULL;
+}
+
+void fbnic_tlv_attr_addr_copy(u8 *dest, struct fbnic_tlv_msg *src)
+{
+	u8 *mac_addr;
+
+	mac_addr = fbnic_tlv_attr_get_value_ptr(src);
+	memcpy(dest, mac_addr, ETH_ALEN);
+}
+
+/**
+ * fbnic_tlv_parser_test_attr - Function loading test attributes into structure
+ * @str: Test structure to load
+ * @results: Pointer to results array
+ *
+ * Copies attributes into structure. Any attribute that doesn't exist in the
+ * results array is not populated.
+ **/
+static void fbnic_tlv_parser_test_attr(struct fbnic_tlv_test *str,
+				       struct fbnic_tlv_msg **results)
+{
+	struct fbnic_tlv_msg *array_results[4];
+	struct fbnic_tlv_msg *attr;
+	char *string = NULL;
+	int i, err;
+
+	str->test_u64 = fta_get_uint(results, FBNIC_TLV_TEST_MSG_U64);
+	str->test_u32 = fta_get_uint(results, FBNIC_TLV_TEST_MSG_U32);
+	str->test_u16 = fta_get_uint(results, FBNIC_TLV_TEST_MSG_U16);
+
+	str->test_s64 = fta_get_sint(results, FBNIC_TLV_TEST_MSG_S64);
+	str->test_s32 = fta_get_sint(results, FBNIC_TLV_TEST_MSG_S32);
+	str->test_s16 = fta_get_sint(results, FBNIC_TLV_TEST_MSG_S16);
+
+	attr = results[FBNIC_TLV_TEST_MSG_MAC_ADDR];
+	if (attr)
+		fbnic_tlv_attr_addr_copy(str->test_mac, attr);
+
+	attr = results[FBNIC_TLV_TEST_MSG_ARRAY];
+	if (attr) {
+		int len = le16_to_cpu(attr->hdr.len) / sizeof(u32) - 1;
+
+		err = fbnic_tlv_attr_parse_array(&attr[1], len,
+						 array_results,
+						 fbnic_tlv_test_index,
+						 FBNIC_TLV_TEST_MSG_MAC_ADDR,
+						 4);
+		if (!err) {
+			for (i = 0; i < 4 && array_results[i]; i++)
+				fbnic_tlv_attr_addr_copy(str->test_mac_array[i],
+							 array_results[i]);
+		}
+	}
+
+	str->test_true = !!results[FBNIC_TLV_TEST_MSG_FLAG_TRUE];
+	str->test_false = !!results[FBNIC_TLV_TEST_MSG_FLAG_FALSE];
+
+	attr = results[FBNIC_TLV_TEST_MSG_STRING];
+	if (attr) {
+		string = fbnic_tlv_attr_get_value_ptr(attr);
+		strscpy(str->test_string, string, FBNIC_TLV_TEST_STRING_LEN);
+	}
+}
+
+static void fbnic_tlv_test_dump(struct fbnic_tlv_test *value, char *prefix)
+{
+	print_hex_dump(KERN_INFO, prefix, DUMP_PREFIX_OFFSET, 16, 1,
+		       value, sizeof(*value), true);
+}
+
+/**
+ * fbnic_tlv_parser_test - Function for parsing and testing test message
+ * @opaque: Unused value
+ * @results: Results of parser output
+ *
+ * Return: negative value on error, or 0 on success.
+ *
+ * Parses attributes to structures and compares the structure to the
+ * expected test value that should have been used to populate the message.
+ *
+ * Used to verify message generation and parser are working correctly.
+ **/
+int fbnic_tlv_parser_test(void *opaque, struct fbnic_tlv_msg **results)
+{
+	struct fbnic_tlv_msg *nest_results[FBNIC_TLV_RESULTS_MAX] = { 0 };
+	struct fbnic_tlv_test result_struct;
+	struct fbnic_tlv_msg *attr;
+	int err;
+
+	memset(&result_struct, 0, sizeof(result_struct));
+	fbnic_tlv_parser_test_attr(&result_struct, results);
+
+	if (memcmp(&test_struct, &result_struct, sizeof(test_struct))) {
+		fbnic_tlv_test_dump(&result_struct, "fbnic: found - ");
+		fbnic_tlv_test_dump(&test_struct, "fbnic: expected - ");
+		return -EINVAL;
+	}
+
+	attr = results[FBNIC_TLV_TEST_MSG_NESTED];
+	if (!attr)
+		return -EINVAL;
+
+	err = fbnic_tlv_attr_parse(&attr[1],
+				   le16_to_cpu(attr->hdr.len) / sizeof(u32) - 1,
+				   nest_results, fbnic_tlv_test_index);
+	if (err)
+		return err;
+
+	memset(&result_struct, 0, sizeof(result_struct));
+	fbnic_tlv_parser_test_attr(&result_struct, nest_results);
+
+	if (memcmp(&test_struct, &result_struct, sizeof(test_struct))) {
+		fbnic_tlv_test_dump(&result_struct, "fbnic: found - ");
+		fbnic_tlv_test_dump(&test_struct, "fbnic: expected - ");
+		return -EINVAL;
+	}
+
+	return 0;
+}

linux-7.2.3/drivers/net/ethernet/meta/fbnic/fbnic_tlv.h

@@ -0,0 +1,185 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) Meta Platforms, Inc. and affiliates. */
+
+#ifndef _FBNIC_TLV_H_
+#define _FBNIC_TLV_H_
+
+#include <asm/byteorder.h>
+#include <linux/bits.h>
+#include <linux/const.h>
+#include <linux/types.h>
+
+struct fbnic_dev;
+
+#define FBNIC_TLV_MSG_ALIGN(len)	ALIGN(len, sizeof(u32))
+#define FBNIC_TLV_MSG_SIZE(len)		\
+		(FBNIC_TLV_MSG_ALIGN(len) / sizeof(u32))
+
+/* TLV Header Format
+ *    3			  2		      1
+ *  1 0 9 8 7 6 5 4 3 2 1 0 9 8 7 6 5 4 3 2 1 0 9 8 7 6 5 4 3 2 1 0
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ * |		Length		   |M|I|RSV|	   Type / ID	   |
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ *
+ * The TLV header format described above will be used for transferring
+ * messages between the host and the firmware. To ensure byte ordering
+ * we have defined all fields as being little endian.
+ * Type/ID: Identifier for message and/or attribute
+ * RSV: Reserved field for future use, likely as additional flags
+ * I: cannot_ignore flag, identifies if unrecognized attribute can be ignored
+ * M: is_msg, indicates that this is the start of a new message
+ * Length: Total length of message in dwords including header
+ *		or
+ *	   Total length of attribute in bytes including header
+ */
+struct fbnic_tlv_hdr {
+#if defined(__LITTLE_ENDIAN_BITFIELD)
+	u16 type		: 12; /* 0 .. 11  Type / ID */
+	u16 rsvd		: 2;  /* 12 .. 13 Reserved for future use */
+	u16 cannot_ignore	: 1;  /* 14	  Attribute can be ignored */
+	u16 is_msg		: 1;  /* 15	  Header belongs to message */
+#elif defined(__BIG_ENDIAN_BITFIELD)
+	u16 is_msg		: 1;  /* 15	  Header belongs to message */
+	u16 cannot_ignore	: 1;  /* 14	  Attribute can be ignored */
+	u16 rsvd		: 2;  /* 13 .. 12 Reserved for future use */
+	u16 type		: 12; /* 11 .. 0  Type / ID */
+#else
+#error "Missing defines from byteorder.h"
+#endif
+	__le16 len;		/* 16 .. 32	length including TLV header */
+};
+
+#define FBNIC_TLV_RESULTS_MAX		32
+
+struct fbnic_tlv_msg {
+	struct fbnic_tlv_hdr	hdr;
+	__le32			value[];
+};
+
+#define FBNIC_TLV_MSG_ID_UNKNOWN		USHRT_MAX
+
+enum fbnic_tlv_type {
+	FBNIC_TLV_STRING,
+	FBNIC_TLV_FLAG,
+	FBNIC_TLV_UNSIGNED,
+	FBNIC_TLV_SIGNED,
+	FBNIC_TLV_BINARY,
+	FBNIC_TLV_NESTED,
+	FBNIC_TLV_ARRAY,
+	__FBNIC_TLV_MAX_TYPE
+};
+
+/* TLV Index
+ * Defines the relationship between the attribute IDs and their types.
+ * For each entry in the index there will be a size and type associated
+ * with it so that we can use this to parse the data and verify it matches
+ * the expected layout.
+ */
+struct fbnic_tlv_index {
+	u16			id;
+	u16			len;
+	enum fbnic_tlv_type	type;
+};
+
+#define TLV_MAX_DATA			((PAGE_SIZE - 512) & 0xFFFF)
+#define FBNIC_TLV_ATTR_ID_UNKNOWN	USHRT_MAX
+#define FBNIC_TLV_ATTR_STRING(id, len)	{ id, len, FBNIC_TLV_STRING }
+#define FBNIC_TLV_ATTR_FLAG(id)		{ id, 0, FBNIC_TLV_FLAG }
+#define FBNIC_TLV_ATTR_U32(id)		{ id, sizeof(u32), FBNIC_TLV_UNSIGNED }
+#define FBNIC_TLV_ATTR_U64(id)		{ id, sizeof(u64), FBNIC_TLV_UNSIGNED }
+#define FBNIC_TLV_ATTR_S32(id)		{ id, sizeof(s32), FBNIC_TLV_SIGNED }
+#define FBNIC_TLV_ATTR_S64(id)		{ id, sizeof(s64), FBNIC_TLV_SIGNED }
+#define FBNIC_TLV_ATTR_MAC_ADDR(id)	{ id, ETH_ALEN, FBNIC_TLV_BINARY }
+#define FBNIC_TLV_ATTR_NESTED(id)	{ id, 0, FBNIC_TLV_NESTED }
+#define FBNIC_TLV_ATTR_ARRAY(id)	{ id, 0, FBNIC_TLV_ARRAY }
+#define FBNIC_TLV_ATTR_RAW_DATA(id)	{ id, TLV_MAX_DATA, FBNIC_TLV_BINARY }
+#define FBNIC_TLV_ATTR_LAST		{ FBNIC_TLV_ATTR_ID_UNKNOWN, 0, 0 }
+
+struct fbnic_tlv_parser {
+	u16				id;
+	const struct fbnic_tlv_index	*attr;
+	int				(*func)(void *opaque,
+						struct fbnic_tlv_msg **results);
+};
+
+#define FBNIC_TLV_PARSER(id, attr, func) { FBNIC_TLV_MSG_ID_##id, attr, func }
+
+static inline void *
+fbnic_tlv_attr_get_value_ptr(struct fbnic_tlv_msg *attr)
+{
+	return (void *)&attr->value[0];
+}
+
+static inline bool fbnic_tlv_attr_get_bool(struct fbnic_tlv_msg *attr)
+{
+	return !!attr;
+}
+
+u64 fbnic_tlv_attr_get_unsigned(struct fbnic_tlv_msg *attr, u64 def);
+s64 fbnic_tlv_attr_get_signed(struct fbnic_tlv_msg *attr, s64 def);
+ssize_t fbnic_tlv_attr_get_string(struct fbnic_tlv_msg *attr, char *dst,
+				  size_t dstsize);
+struct fbnic_tlv_msg *fbnic_tlv_msg_alloc(u16 msg_id);
+int fbnic_tlv_attr_put_flag(struct fbnic_tlv_msg *msg, const u16 attr_id);
+int fbnic_tlv_attr_put_value(struct fbnic_tlv_msg *msg, const u16 attr_id,
+			     const void *value, const int len);
+int __fbnic_tlv_attr_put_int(struct fbnic_tlv_msg *msg, const u16 attr_id,
+			     s64 value, const int len);
+#define fbnic_tlv_attr_put_int(msg, attr_id, value) \
+	__fbnic_tlv_attr_put_int(msg, attr_id, value, \
+				 FBNIC_TLV_MSG_ALIGN(sizeof(value)))
+int fbnic_tlv_attr_put_mac_addr(struct fbnic_tlv_msg *msg, const u16 attr_id,
+				const u8 *mac_addr);
+int fbnic_tlv_attr_put_string(struct fbnic_tlv_msg *msg, u16 attr_id,
+			      const char *string);
+struct fbnic_tlv_msg *fbnic_tlv_attr_nest_start(struct fbnic_tlv_msg *msg,
+						u16 attr_id);
+void fbnic_tlv_attr_nest_stop(struct fbnic_tlv_msg *msg);
+void fbnic_tlv_attr_addr_copy(u8 *dest, struct fbnic_tlv_msg *src);
+int fbnic_tlv_attr_parse_array(struct fbnic_tlv_msg *attr, int len,
+			       struct fbnic_tlv_msg **results,
+			       const struct fbnic_tlv_index *tlv_index,
+			       u16 tlv_attr_id, size_t array_len);
+int fbnic_tlv_attr_parse(struct fbnic_tlv_msg *attr, int len,
+			 struct fbnic_tlv_msg **results,
+			 const struct fbnic_tlv_index *tlv_index);
+int fbnic_tlv_msg_parse(void *opaque, struct fbnic_tlv_msg *msg,
+			const struct fbnic_tlv_parser *parser);
+int fbnic_tlv_parser_error(void *opaque, struct fbnic_tlv_msg **results);
+
+#define fta_get_uint(_results, _id) \
+	fbnic_tlv_attr_get_unsigned(_results[_id], 0)
+#define fta_get_sint(_results, _id) \
+	fbnic_tlv_attr_get_signed(_results[_id], 0)
+#define fta_get_str(_results, _id, _dst, _dstsize) \
+	fbnic_tlv_attr_get_string(_results[_id], _dst, _dstsize)
+
+#define FBNIC_TLV_MSG_ID_TEST	0
+
+enum fbnic_tlv_test_attr_id {
+	FBNIC_TLV_TEST_MSG_U64,
+	FBNIC_TLV_TEST_MSG_S64,
+	FBNIC_TLV_TEST_MSG_U32,
+	FBNIC_TLV_TEST_MSG_S32,
+	FBNIC_TLV_TEST_MSG_U16,
+	FBNIC_TLV_TEST_MSG_S16,
+	FBNIC_TLV_TEST_MSG_MAC_ADDR,
+	FBNIC_TLV_TEST_MSG_FLAG_TRUE,
+	FBNIC_TLV_TEST_MSG_FLAG_FALSE,
+	FBNIC_TLV_TEST_MSG_STRING,
+	FBNIC_TLV_TEST_MSG_NESTED,
+	FBNIC_TLV_TEST_MSG_ARRAY,
+	FBNIC_TLV_TEST_MSG_MAX
+};
+
+extern const struct fbnic_tlv_index fbnic_tlv_test_index[];
+struct fbnic_tlv_msg *fbnic_tlv_test_create(struct fbnic_dev *fbd);
+int fbnic_tlv_parser_test(void *opaque, struct fbnic_tlv_msg **results);
+
+#define FBNIC_TLV_MSG_TEST \
+	FBNIC_TLV_PARSER(TEST, fbnic_tlv_test_index, \
+			 fbnic_tlv_parser_test)
+#define FBNIC_TLV_MSG_ERROR \
+	FBNIC_TLV_PARSER(UNKNOWN, NULL, fbnic_tlv_parser_error)
+#endif /* _FBNIC_TLV_H_ */

linux-7.2.3/drivers/net/ethernet/meta/fbnic/fbnic_txrx.h

@@ -0,0 +1,207 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) Meta Platforms, Inc. and affiliates. */
+
+#ifndef _FBNIC_TXRX_H_
+#define _FBNIC_TXRX_H_
+
+#include <linux/netdevice.h>
+#include <linux/skbuff.h>
+#include <linux/types.h>
+#include <linux/u64_stats_sync.h>
+#include <net/xdp.h>
+
+struct fbnic_net;
+
+/* Guarantee we have space needed for storing the buffer
+ * To store the buffer we need:
+ *	1 descriptor per page
+ *	+ 1 descriptor for skb head
+ *	+ 2 descriptors for metadata and optional metadata
+ *	+ 7 descriptors to keep tail out of the same cacheline as head
+ * If we cannot guarantee that then we should return TX_BUSY
+ */
+#define FBNIC_MAX_SKB_DESC	(MAX_SKB_FRAGS + 10)
+#define FBNIC_TX_DESC_WAKEUP	(FBNIC_MAX_SKB_DESC * 2)
+#define FBNIC_TX_DESC_MIN	roundup_pow_of_two(FBNIC_TX_DESC_WAKEUP)
+
+/* To receive the worst case packet we need:
+ *	1 descriptor for primary metadata
+ *	+ 1 descriptor for optional metadata
+ *	+ 1 descriptor for headers
+ *	+ 4 descriptors for payload
+ */
+#define FBNIC_MAX_RX_PKT_DESC	7
+#define FBNIC_RX_DESC_MIN	roundup_pow_of_two(FBNIC_MAX_RX_PKT_DESC * 2)
+
+#define FBNIC_MAX_TXQS			128u
+#define FBNIC_MAX_RXQS			128u
+#define FBNIC_MAX_XDPQS			128u
+
+/* These apply to TWQs, TCQ, RCQ */
+#define FBNIC_QUEUE_SIZE_MIN		64u
+#define FBNIC_QUEUE_SIZE_MAX		SZ_64K
+
+#define FBNIC_TXQ_SIZE_DEFAULT		1024
+#define FBNIC_HPQ_SIZE_DEFAULT		256
+#define FBNIC_PPQ_SIZE_DEFAULT		256
+#define FBNIC_RCQ_SIZE_DEFAULT		1024
+#define FBNIC_TX_USECS_DEFAULT		35
+#define FBNIC_RX_USECS_DEFAULT		30
+#define FBNIC_RX_FRAMES_DEFAULT		0
+
+#define FBNIC_RX_TROOM \
+	SKB_DATA_ALIGN(sizeof(struct skb_shared_info))
+#define FBNIC_RX_HROOM_PAD		128
+#define FBNIC_RX_HROOM \
+	(ALIGN(FBNIC_RX_TROOM + FBNIC_RX_HROOM_PAD, 128) - FBNIC_RX_TROOM)
+#define FBNIC_RX_PAD			0
+#define FBNIC_RX_PAYLD_OFFSET		0
+#define FBNIC_RX_PAYLD_PG_CL		0
+
+#define FBNIC_RING_F_DISABLED		BIT(0)
+#define FBNIC_RING_F_CTX		BIT(1)
+#define FBNIC_RING_F_STATS		BIT(2)	/* Ring's stats may be used */
+
+#define FBNIC_HDS_THRESH_MAX \
+	(4096 - FBNIC_RX_HROOM - FBNIC_RX_TROOM - FBNIC_RX_PAD)
+#define FBNIC_HDS_THRESH_DEFAULT \
+	(1536 - FBNIC_RX_PAD)
+#define FBNIC_HDR_BYTES_MIN		256
+
+struct fbnic_pkt_buff {
+	struct xdp_buff buff;
+	ktime_t hwtstamp;
+	bool add_frag_failed;
+};
+
+struct fbnic_queue_stats {
+	u64 packets;
+	u64 bytes;
+	union {
+		struct {
+			u64 csum_partial;
+			u64 lso;
+			u64 ts_packets;
+			u64 ts_lost;
+			u64 stop;
+			u64 wake;
+		} twq;
+		struct {
+			u64 alloc_failed;
+			u64 csum_complete;
+			u64 csum_none;
+			u64 length_errors;
+		} rx;
+		struct {
+			u64 alloc_failed;
+		} bdq;
+	};
+	u64 dropped;
+	struct u64_stats_sync syncp;
+};
+
+#define FBNIC_PAGECNT_BIAS_MAX	PAGE_SIZE
+
+struct fbnic_rx_buf {
+	netmem_ref netmem;
+	long pagecnt_bias;
+};
+
+struct fbnic_ring {
+	/* Pointer to buffer specific info */
+	union {
+		struct fbnic_pkt_buff *pkt;	/* RCQ */
+		struct fbnic_rx_buf *rx_buf;	/* BDQ */
+		void **tx_buf;			/* TWQ */
+		void *buffer;			/* Generic pointer */
+	};
+
+	u32 __iomem *doorbell;		/* Pointer to CSR space for ring */
+	__le64 *desc;			/* Descriptor ring memory */
+	u16 size_mask;			/* Size of ring in descriptors - 1 */
+	u8 q_idx;			/* Logical netdev ring index */
+	u8 flags;			/* Ring flags (FBNIC_RING_F_*) */
+
+	u32 head, tail;			/* Head/Tail of ring */
+
+	union {
+		/* Rx BDQs only */
+		struct page_pool *page_pool;
+
+		/* Deferred_head is used to cache the head for TWQ1 if
+		 * an attempt is made to clean TWQ1 with zero napi_budget.
+		 * We do not use it for any other ring.
+		 */
+		s32 deferred_head;
+	};
+
+	struct fbnic_queue_stats stats;
+
+	/* Slow path fields follow */
+	dma_addr_t dma;			/* Phys addr of descriptor memory */
+	size_t size;			/* Size of descriptor ring in memory */
+};
+
+struct fbnic_q_triad {
+	struct fbnic_ring sub0, sub1, cmpl;
+	struct xdp_rxq_info xdp_rxq;
+};
+
+struct fbnic_napi_vector {
+	struct napi_struct napi;
+	struct device *dev;		/* Device for DMA unmapping */
+	struct fbnic_dev *fbd;
+	struct dentry *dbg_nv;
+
+	u16 v_idx;
+	u8 txt_count;
+	u8 rxt_count;
+
+	struct fbnic_q_triad qt[];
+};
+
+extern const struct netdev_queue_mgmt_ops fbnic_queue_mgmt_ops;
+
+netdev_tx_t fbnic_xmit_frame(struct sk_buff *skb, struct net_device *dev);
+netdev_features_t
+fbnic_features_check(struct sk_buff *skb, struct net_device *dev,
+		     netdev_features_t features);
+
+void fbnic_aggregate_ring_rx_counters(struct fbnic_net *fbn,
+				      struct fbnic_ring *rxr);
+void fbnic_aggregate_ring_bdq_counters(struct fbnic_net *fbn,
+				       struct fbnic_ring *rxr);
+void fbnic_aggregate_ring_tx_counters(struct fbnic_net *fbn,
+				      struct fbnic_ring *txr);
+void fbnic_aggregate_ring_xdp_counters(struct fbnic_net *fbn,
+				       struct fbnic_ring *xdpr);
+
+int fbnic_alloc_napi_vectors(struct fbnic_net *fbn);
+void fbnic_free_napi_vectors(struct fbnic_net *fbn);
+int fbnic_alloc_resources(struct fbnic_net *fbn);
+void fbnic_free_resources(struct fbnic_net *fbn);
+int fbnic_set_netif_queues(struct fbnic_net *fbn);
+void fbnic_reset_netif_queues(struct fbnic_net *fbn);
+irqreturn_t fbnic_msix_clean_rings(int irq, void *data);
+void fbnic_napi_enable(struct fbnic_net *fbn);
+void fbnic_napi_disable(struct fbnic_net *fbn);
+void fbnic_config_drop_mode(struct fbnic_net *fbn, bool tx_pause);
+void fbnic_enable(struct fbnic_net *fbn);
+void fbnic_disable(struct fbnic_net *fbn);
+void fbnic_dbg_up(struct fbnic_net *fbn);
+void fbnic_dbg_down(struct fbnic_net *fbn);
+void fbnic_flush(struct fbnic_net *fbn);
+void fbnic_fill(struct fbnic_net *fbn);
+
+u32 __iomem *fbnic_ring_csr_base(const struct fbnic_ring *ring);
+void fbnic_napi_depletion_check(struct net_device *netdev);
+int fbnic_wait_all_queues_idle(struct fbnic_dev *fbd, bool may_fail);
+
+static inline int fbnic_napi_idx(const struct fbnic_napi_vector *nv)
+{
+	return nv->v_idx - FBNIC_NON_NAPI_VECTORS;
+}
+
+void fbnic_dbg_nv_init(struct fbnic_napi_vector *nv);
+void fbnic_dbg_nv_exit(struct fbnic_napi_vector *nv);
+#endif /* _FBNIC_TXRX_H_ */